© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13945
    Prev
    Next
    INDEX
    Explanations

    code file paths ending in `.scss` used for Angular components

    oai_token-act-pair · gemini-2.0-flash

    period tokens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    RegressionTest
    -1.02
    Попис
    -1.00
    帖最后由
    -0.92
     '\\;'
    -0.90
     ModelExpression
    -0.89
     ProtoMessage
    -0.86
    webElementXpaths
    -0.85
     mergeFrom
    -0.84
     cherchés
    -0.82
    SharedCtor
    -0.77
    POSITIVE LOGITS
     sa
    0.46
    Ծանոթ
    0.45
    getWriter
    0.42
    otis
    0.41
     last
    0.38
    iori
    0.38
    arif
    0.36
    univ
    0.36
     General
    0.36
    iffel
    0.35
    Activations Density 0.154%

    No Known Activations