© 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. 14655
    Prev
    Next
    INDEX
    Explanations

    words or phrases characteristic of scientific publications.

    oai_token-act-pair · gemini-2.0-flash

    statistics

    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
    izer
    -0.50
    ep
    -0.50
    cill
    -0.48
     تص
    -0.48
     Tight
    -0.46
    ρέ
    -0.46
    <eos>
    -0.45
    libft
    -0.45
    fonts
    -0.45
    𝘷
    -0.45
    POSITIVE LOGITS
     betweenstory
    0.68
    ^(@)
    0.68
    клопе
    0.65
     itſelf
    0.63
    Климат
    0.63
    Xna
    0.61
     myſelf
    0.60
     Monfieur
    0.60
    帖最后由
    0.60
    حياتها
    0.60
    Activations Density 7.390%

    No Known Activations