© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5234
    Prev
    Next
    INDEX
    Explanations

    sentence delimiters at the ends of phrases or sentences

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Referencies
    -0.50
     now
    -0.50
     he
    -0.46
    strSql
    -0.44
     agama
    -0.44
     <<<<<<<<<<<<<<
    -0.44
    igshid
    -0.43
     palmas
    -0.43
     ahora
    -0.43
     agora
    -0.42
    POSITIVE LOGITS
    parsedMessage
    0.71
     AssemblyProduct
    0.69
    InjectAttribute
    0.66
    OrBuilder
    0.65
     Efq
    0.63
     BoxFit
    0.59
    Personendaten
    0.59
    SourceChecksum
    0.58
    })();
    0.58
    inspace
    0.58
    Activations Density 0.899%

    No Known Activations