© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12386
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially from Javascript tests

    oai_token-act-pair · gemini-2.0-flash

    code debug mode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    うん
    -0.47
     اكتوبر
    -0.47
    󠁴
    -0.46
    帖最后由
    -0.45
     Style
    -0.45
    plotlib
    -0.45
     cầu
    -0.43
    ực
    -0.43
    daging
    -0.43
     Fine
    -0.43
    POSITIVE LOGITS
     chofe
    0.74
     auffi
    0.72
     reaſon
    0.71
     neceſſ
    0.70
     uſ
    0.70
     ſeveral
    0.69
     itſelf
    0.68
     ſtill
    0.67
     poffible
    0.66
     fhort
    0.65
    Activations Density 2.545%

    No Known Activations