© 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. 58210
    Prev
    Next
    INDEX
    Explanations

    back door

    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
     I
    1.41
     <
    0.95
     in
    0.90
     в
    0.86
     a
    0.86
     he
    0.86
    ;
    0.85
    ".
    0.84
     \
    0.83
    ).
    0.82
    POSITIVE LOGITS
    ла
    1.73
    ви
    1.56
    ف
    1.55
    ش
    1.54
    리
    1.45
    า
    1.33
    기
    1.33
    وک
    1.31
    де
    1.30
    يا
    1.26
    Activations Density 0.002%

    No Known Activations