© 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. 3440
    Prev
    Next
    INDEX
    Explanations

    references to figures, schemes, and tables in scientific papers

    oai_token-act-pair · gemini-2.0-flash

    [

    np_max-act-logits · 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
    (
    -0.94
    ,
    -0.81
    -
    -0.77
    .
    -0.68
     (
    -0.60
     at
    -0.60
    :
    -0.59
     di
    -0.57
     in
    -0.57
    ↵
    -0.57
    POSITIVE LOGITS
     itſelf
    1.17
     myſelf
    1.10
     Diſ
    1.01
     Efq
    0.99
     Monfieur
    0.98
    ſelf
    0.94
     ſche
    0.93
     pleaſure
    0.93
     raiſ
    0.91
     reaſon
    0.91
    Activations Density 6.725%

    No Known Activations