© 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-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193275
    Prev
    Next
    INDEX
    Explanations

    getting noticed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    1.11
    0.97
    &
    0.79
    >
    0.67
    ре
    0.66
    ви
    0.66
    -
    0.64
    '
    0.64
    คุณ
    0.63
    uğu
    0.62
    POSITIVE LOGITS
    as
    0.92
    a
    0.91
    u
    0.83
     as
    0.74
    이었
    0.73
     a
    0.71
     consistente
    0.66
    の
    0.66
     smuggled
    0.65
     integrante
    0.64
    Activations Density 0.006%

    No Known Activations