© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8595
    Prev
    Next
    INDEX
    Explanations

    words denoting attractiveness or popularity of some kind

    oai_token-act-pair · gemini-2.0-flash

    appeal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    SourceChecksum
    -0.96
     تانيه
    -0.70
    FieldNumber
    -0.69
     كومونز
    -0.68
    ArrowToggle
    -0.68
     OFDb
    -0.67
    setVerticalGroup
    -0.66
    OrBuilder
    -0.66
    TagMode
    -0.66
    PageRoute
    -0.65
    POSITIVE LOGITS
     appeal
    1.47
    appeal
    1.13
     Appeal
    1.09
    Appeal
    1.04
     APPEAL
    1.04
     attraction
    0.91
     popularity
    0.91
     appealing
    0.89
     appeals
    0.88
     allure
    0.88
    Activations Density 0.968%

    No Known Activations