© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14000
    Prev
    Next
    INDEX
    Explanations

    code snippets related to retrieving language names

    oai_token-act-pair · gemini-2.0-flash

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ArgsConstructor
    -0.68
    ScopeManager
    -0.62
     gratuites
    -0.60
    findpost
    -0.57
     getItemId
    -0.56
    CurrentValue
    -0.53
    ραγ
    -0.52
    ReusableCell
    -0.52
     Lleva
    -0.51
     ArrayAdapter
    -0.50
    POSITIVE LOGITS
    StructEnd
    0.61
    Források
    0.60
    titleMargin
    0.52
    canakan
    0.48
     OFDb
    0.48
    piratory
    0.47
    Demografia
    0.45
    sonaro
    0.44
     caracteriza
    0.44
    enterOuterAlt
    0.43
    Activations Density 0.963%

    No Known Activations