© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13901
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially last names

    oai_token-act-pair · gemini-2.0-flash

    names/places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     purpoſe
    -0.75
     myſelf
    -0.72
     fubject
    -0.72
     ſtate
    -0.66
     Efq
    -0.63
     quæ
    -0.62
     Theſe
    -0.62
     HasFactory
    -0.62
     Majefty
    -0.61
     whoſe
    -0.59
    POSITIVE LOGITS
    <bos>
    0.76
    MathML
    0.56
    featureID
    0.53
    Билгалдахарш
    0.52
     архивлан
    0.50
    ArgsConstructor
    0.48
    postIndex
    0.47
    WriteBarrier
    0.47
    EndInit
    0.47
    WireFormatLite
    0.46
    Activations Density 1.769%

    No Known Activations