© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10861
    Prev
    Next
    INDEX
    Explanations

    math formulas and expressions

    oai_token-act-pair · gemini-2.0-flash

    code/equations/foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     kasarigan
    -0.52
    EDEFAULT
    -0.48
    UrlResolution
    -0.47
    ~•
    -0.47
     HttpNotFound
    -0.43
    theoremstyle
    -0.43
     agr
    -0.43
    simpleType
    -0.41
    nextProps
    -0.41
     ModelExpression
    -0.41
    POSITIVE LOGITS
    кування
    0.61
    âtre
    0.58
    oredCriteria
    0.57
    Під
    0.56
     між
    0.56
     tchèque
    0.56
     traité
    0.55
     nahilalakip
    0.54
     з
    0.54
    Ін
    0.54
    Activations Density 12.666%

    No Known Activations