© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14389
    Prev
    Next
    INDEX
    Explanations

    programming code, especially related to 3D graphics or database queries

    oai_token-act-pair · gemini-2.0-flash

    words related to self-referential terms

    np_token-act-pair-logits · gpt-4o-mini

    Code/File syntax

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     
    -0.89
    ↵
    -0.88
    ↵↵
    -0.81
    ,
    -0.79
     [
    -0.76
     "
    -0.75
     H
    -0.75
     I
    -0.75
     $\
    -0.75
     $
    -0.73
    POSITIVE LOGITS
     Efq
    1.15
     itſelf
    1.13
     doubtnut
    1.04
     faſt
    0.97
     myſelf
    0.96
    ſelf
    0.94
     raiſ
    0.94
    ſelves
    0.93
     auffi
    0.92
     edelstahl
    0.90
    Activations Density 9.214%

    No Known Activations