© 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. 14762
    Prev
    Next
    INDEX
    Explanations

    code snippets, formulas or symbolic representations

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
    Parce
    -0.47
     again
    -0.45
    UELA
    -0.43
    HttpConnection
    -0.42
    uela
    -0.42
     tional
    -0.42
    enem
    -0.42
    vice
    -0.41
    uelas
    -0.41
     Kerk
    -0.41
    POSITIVE LOGITS
    RegistryLite
    0.77
    HostException
    0.71
     للمعارف
    0.70
     kasarigan
    0.68
    GIH
    0.55
     vux
    0.55
    EndContext
    0.53
     linkovi
    0.51
    GeoNames
    0.51
     дописавши
    0.51
    Activations Density 6.347%

    No Known Activations