© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7257
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and markup

    oai_token-act-pair · gemini-2.0-flash

    symbols and code-related terms

    np_token-act-pair-logits · gpt-4o-mini

    $

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    
    -0.68
    })`
    -0.65
     estekak
    -0.65
     ModelExpression
    -0.62
     թվական
    -0.61
    tvguidetime
    -0.60
     gddr
    -0.58
     dreamstime
    -0.57
     gyhoeddwyd
    -0.57
     فريبيس
    -0.57
    POSITIVE LOGITS
     onCancelled
    0.56
    DispatchToProps
    0.51
     đạp
    0.49
    getCause
    0.48
    rdom
    0.46
    LogFactory
    0.46
    Diwedd
    0.46
     plomo
    0.44
    купить
    0.44
    raux
    0.43
    Activations Density 0.719%

    No Known Activations