© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12265
    Prev
    Next
    INDEX
    Explanations

    discussion of problems and solutions, likely in a forum context

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    migrationBuilder
    -0.73
    <bos>
    -0.72
    存于互联网档案馆
    -0.66
     beginnetje
    -0.64
     كومونز
    -0.63
    GeoNames
    -0.60
     примеру
    -0.59
    sizeCache
    -0.58
     ویکی‌پدیای
    -0.57
     bezeichneter
    -0.56
    POSITIVE LOGITS
    UrlResolution
    0.56
    crites
    0.52
    djangoproject
    0.48
     SEDS
    0.45
    ządu
    0.44
     WALTZ
    0.44
    PickerController
    0.44
     @"/
    0.43
     band
    0.42
     समीक्षक
    0.42
    Activations Density 0.630%

    No Known Activations