© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1865
    Prev
    Next
    INDEX
    Explanations

    code snippets, or words that often appear in code

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     ProtoMessage
    -0.67
    లాలు
    -0.66
    SourceChecksum
    -0.65
    MENAFN
    -0.62
    Referanser
    -0.62
    ]")]
    -0.61
     мәкал
    -0.61
    EDEFAULT
    -0.60
    AnchorStyles
    -0.60
    webElementXpaths
    -0.57
    POSITIVE LOGITS
     szól
    0.50
    canto
    0.47
    IntoConstraints
    0.47
    neiden
    0.46
    prehension
    0.46
    förs
    0.46
    inkt
    0.45
    astify
    0.44
     crossorigin
    0.44
     digitais
    0.43
    Activations Density 12.033%

    No Known Activations