© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9574
    Prev
    Next
    INDEX
    Explanations

    stack traces from python scripts

    oai_token-act-pair · gemini-2.0-flash

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    TagMode
    -1.11
    Personensuche
    -1.05
    oa̍t
    -0.85
     للاسماء
    -0.82
     Италијани
    -0.81
    Vidite
    -0.80
    webElementXpaths
    -0.79
    Autoritní
    -0.76
    LookAnd
    -0.73
     صوتيه
    -0.73
    POSITIVE LOGITS
    ipy
    0.42
    充
    0.39
     ModelRenderer
    0.37
     khả
    0.37
     vyu
    0.36
    tilli
    0.36
    cmd
    0.36
     CONT
    0.36
     susten
    0.35
    썬
    0.35
    Activations Density 0.311%

    No Known Activations