© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41740
    Prev
    Next
    INDEX
    Explanations

    woodsy Elf Ranger

    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_3_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
    ’
    1.02
    apro
    0.79
    اک
    0.75
    -
    0.75
    ové
    0.71
    {}
    0.70
    yb
    0.69
     قائم
    0.69
    ip
    0.67
    {},
    0.66
    POSITIVE LOGITS
    <0x0D>
    0.98
    ی
    0.76
    0.76
     inquirer
    0.72
    ﺔ
    0.71
     exclu
    0.71
     inhaled
    0.69
     adul
    0.68
    I
    0.67
    Ы
    0.67
    Activations Density 0.000%

    No Known Activations