© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62784
    Prev
    Next
    INDEX
    Explanations

    prisons

    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
    Negative Logits
    ка
    1.83
    د
    1.65
    ا
    1.52
    ك
    1.52
    ма
    1.48
    、
    1.42
    ุ
    1.38
    و
    1.38
    ح
    1.33
    ના
    1.31
    POSITIVE LOGITS
     K
    1.20
    li
    1.18
     by
    1.17
    -
    1.17
     I
    1.13
     with
    1.12
     from
    1.12
    ט
    1.11
    يد
    1.10
    ী
    1.10
    Activations Density 0.000%

    No Known Activations