© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108378
    Prev
    Next
    INDEX
    Explanations

    blanc and Blanco

    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_2_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
    .
    1.50
    '
    1.48
    रे
    1.17
    .。
    1.08
    ۔
    1.03
    "
    1.01
    ने
    1.00
    p
    0.99
    ü
    0.98
    ב
    0.98
    POSITIVE LOGITS
    тят
    1.01
    聁
    0.95
    ت
    0.95
    tgt
    0.94
    t
    0.94
    تش
    0.93
    ennzeichnet
    0.93
    ية
    0.91
    на
    0.90
    تين
    0.89
    Activations Density 0.000%

    No Known Activations