© 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. 9417
    Prev
    Next
    INDEX
    Explanations

    code snippets and date-related variables

    oai_token-act-pair · gemini-2.0-flash

    Dates and times

    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
     Widodo
    -0.56
     ویکی‌پدیا
    -0.48
    migrationBuilder
    -0.47
    ädie
    -0.45
    atory
    -0.45
    </thead>
    -0.44
    inah
    -0.43
    :///
    -0.43
     Beller
    -0.42
     gọn
    -0.42
    POSITIVE LOGITS
     dates
    1.30
     date
    1.28
    date
    1.09
     timing
    1.09
     Dates
    1.07
     time
    1.03
     timetable
    1.02
     timings
    1.02
     DATE
    1.02
     Date
    1.02
    Activations Density 18.392%

    No Known Activations