© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142263
    Prev
    Next
    INDEX
    Explanations

    minefields

    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_12_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
    F
    0.21
    H
    0.21
    D
    0.20
    P
    0.20
    I
    0.19
    Seine
    0.19
    Health
    0.19
    Turns
    0.19
    C
    0.19
    Oi
    0.19
    POSITIVE LOGITS
     ""),
    0.19
     леса
    0.19
     obviamente
    0.18
    ты
    0.18
    cstdlib
    0.18
    ిత
    0.18
    eworthy
    0.17
     leyenda
    0.17
     transvers
    0.17
     ゲーム
    0.17
    Activations Density 0.000%

    No Known Activations