© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 23881
    Prev
    Next
    INDEX
    Explanations

    get out of

    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_10_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
    inei
    0.55
    c
    0.54
    O
    0.53
    น่า
    0.52
    ahankan
    0.52
    ihkan
    0.52
    sh
    0.51
    ன்மை
    0.51
    );
    0.50
    ine
    0.50
    POSITIVE LOGITS
     escape
    0.96
     escaping
    0.71
     escapes
    0.68
    逃
    0.66
     fuga
    0.65
     escapar
    0.64
     Escape
    0.64
    ল
    0.64
    escape
    0.63
     jail
    0.61
    Activations Density 0.019%

    No Known Activations