© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1518
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and expressions indicative of scientific research.

    oai_token-act-pair · gemini-2.0-flash

    academic research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -1.21
     defaultstate
    -0.82
    ⓧ
    -0.76
     ModelExpression
    -0.71
    #
    -0.71
    FundMe
    -0.70
    ImageContext
    -0.68
     autorytatywna
    -0.68
    Autoritní
    -0.66
     &___
    -0.66
    POSITIVE LOGITS
    tising
    0.41
    ClassPath
    0.41
    irmish
    0.40
    RoutingModule
    0.40
    .--
    0.39
    pakk
    0.39
    VISIBLE
    0.39
    caris
    0.39
    σμα
    0.39
    plom
    0.38
    Activations Density 9.751%

    No Known Activations