© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1936
    Prev
    Next
    INDEX
    Explanations

    words related to machines and mechanical processes

    oai_token-act-pair · gemini-2.0-flash

    components related to machinery and mechanics

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

    Belts and cams

    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
    脚注の使い方
    -0.70
     pleaſure
    -0.57
     Theſe
    -0.54
     caufe
    -0.53
     Majefty
    -0.52
    BibitemShut
    -0.52
     Anſ
    -0.52
     Rueda
    -0.52
     Prolog
    -0.52
    তথ্যসূত্র
    -0.51
    POSITIVE LOGITS
     tension
    0.58
     belt
    0.56
     cam
    0.56
    belt
    0.54
     Cam
    0.54
    $__
    0.54
    arakhand
    0.53
     Belt
    0.53
    Tension
    0.52
     himo
    0.52
    Activations Density 1.241%

    No Known Activations