© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4587
    Prev
    Next
    INDEX
    Explanations

    words associated with research and analysis, and personal writing/blogging

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    .
    -1.20
    ,
    -0.90
    ;
    -0.81
    :
    -0.69
    <eos>
    -0.69
    ↵↵
    -0.67
    !
    -0.67
    ↵
    -0.65
    ).
    -0.63
     
    -0.60
    POSITIVE LOGITS
     itſelf
    1.55
     myſelf
    1.53
     Efq
    1.47
     Monfieur
    1.33
    ſelves
    1.28
     Majefty
    1.27
     purpoſe
    1.25
     raiſ
    1.25
     himſelf
    1.24
     ſeveral
    1.24
    Activations Density 13.623%

    No Known Activations