© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90231
    Prev
    Next
    INDEX
    Explanations

    criminal acts and offenses

    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_11_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
    de
    0.63
    IN
    0.57
    n
    0.57
    ي
    0.53
    ml
    0.51
    re
    0.50
    ו
    0.50
    nb
    0.49
    ana
    0.49
    nn
    0.47
    POSITIVE LOGITS
     스스로
    0.49
    overleftarrow
    0.46
     می‌تواند
    0.45
     دوسروں
    0.45
    ﮭ
    0.44
     bây
    0.43
    ﭥ
    0.43
    쇄
    0.42
     amalgamated
    0.41
    쯔
    0.41
    Activations Density 0.003%

    No Known Activations