© 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. 126244
    Prev
    Next
    INDEX
    Explanations

    simulation results

    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
    的
    0.58
     sabbam
    0.56
     احتيا
    0.55
     namani
    0.54
     kaikki
    0.54
    esorios
    0.54
     Sección
    0.54
    dır
    0.54
    e
    0.54
    اي
    0.53
    POSITIVE LOGITS
    .
    0.97
    '
    0.85
    ନ
    0.82
    २
    0.70
    CTION
    0.69
     avenues
    0.69
    і
    0.68
    *
    0.67
    on
    0.67
    かわいい
    0.66
    Activations Density 0.000%

    No Known Activations