© 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. 6997
    Prev
    Next
    INDEX
    Explanations

    statistical language, particularly percentages, fractions, and comparisons

    oai_token-act-pair · gemini-2.0-flash

    comparative terms

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

    Approximations and proportions

    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
    addCriterion
    -0.86
     nakalista
    -0.78
    nearly
    -0.76
     estekak
    -0.75
    ">//
    -0.74
     متعلقه
    -0.73
     reaſon
    -0.71
     Majefty
    -0.69
     nearly
    -0.68
     ModelExpression
    -0.68
    POSITIVE LOGITS
     Equal
    0.54
     equal
    0.50
     prochains
    0.46
     navideños
    0.45
     banho
    0.44
    Equal
    0.44
     irmãos
    0.43
    herin
    0.42
     irmão
    0.42
     kijken
    0.41
    Activations Density 0.840%

    No Known Activations