© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11970
    Prev
    Next
    INDEX
    Explanations

    periods in links and URLs

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    UrlEncoded
    -0.47
    новништво
    -0.46
     Anti
    -0.45
    <bos>
    -0.44
     Natur
    -0.43
    typeorm
    -0.43
     compositeur
    -0.42
    Становништво
    -0.41
     All
    -0.40
     kỳ
    -0.40
    POSITIVE LOGITS
     Efq
    0.81
    jardins
    0.70
     myſelf
    0.65
     itſelf
    0.62
     neceſſ
    0.61
     arşivlendi
    0.61
     neceffary
    0.61
     nakalista
    0.60
     neceff
    0.60
     GIPHY
    0.58
    Activations Density 0.262%

    No Known Activations