© 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. 10948
    Prev
    Next
    INDEX
    Explanations

    references to lengths of time

    oai_token-act-pair · gemini-2.0-flash

    Small quantity

    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>
    -1.20
    fromnode
    -0.60
    ampingi
    -0.55
     uſed
    -0.53
    حياته
    -0.52
    WireFormatLite
    -0.52
     électroniques
    -0.50
     Jefus
    -0.50
    <!--[
    -0.49
    ✭✭
    -0.49
    POSITIVE LOGITS
     للمعارف
    0.68
    ThroughAttribute
    0.64
    EDEFAULT
    0.63
    PageRoute
    0.59
     OFDb
    0.59
    onViewCreated
    0.58
     getRule
    0.55
    ErrUnexpectedEOF
    0.54
    addCriterion
    0.54
    isman
    0.53
    Activations Density 8.279%

    No Known Activations