© 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. 2913
    Prev
    Next
    INDEX
    Explanations

    references to data presented in tables.

    oai_token-act-pair · gemini-2.0-flash

    references to tables or data

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

    Table

    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
    mybatisplus
    -0.79
    Попис
    -0.77
    featureID
    -0.72
    orescence
    -0.68
    twimg
    -0.68
    ifflin
    -0.68
    ########.
    -0.66
    Personensuche
    -0.66
     ChromeDriver
    -0.66
    resizingMask
    -0.65
    POSITIVE LOGITS
    tslib
    0.43
    arn
    0.43
     merce
    0.43
    Mer
    0.42
    service
    0.42
    top
    0.41
    viewBox
    0.40
    onec
    0.40
    cloth
    0.40
    Pepper
    0.40
    Activations Density 1.642%

    No Known Activations