© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8252
    Prev
    Next
    INDEX
    Explanations

    short alphanumeric strings with occasional special characters

    oai_token-act-pair · gemini-2.0-flash

    code/file paths

    np_max-act-logits · gemini-2.0-flash

    say "single characters" Method used: 2 — because tokens after max activating are single-character tokens — say "single characters"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     élas
    -0.50
     publiques
    -0.47
     Nazionale
    -0.47
     vulga
    -0.47
     nationales
    -0.47
    쁜
    -0.46
     nationaux
    -0.45
     irré
    -0.44
     eorum
    -0.44
    ті
    -0.43
    POSITIVE LOGITS
    UnusedPrivate
    0.88
    ]")]
    0.84
    SourceChecksum
    0.82
    oredCriteria
    0.75
    yntaxException
    0.74
     betweenstory
    0.73
     ExecuteAsync
    0.71
     IndexPath
    0.71
    OGND
    0.70
    ElementException
    0.70
    Activations Density 4.106%

    No Known Activations