© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 60058
    Prev
    Next
    INDEX
    Explanations

    crime

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     found
    0.41
    ч
    0.37
     津
    0.36
    溏
    0.36
    Found
    0.34
    found
    0.34
     coded
    0.34
    cons
    0.33
     Chia
    0.33
    博
    0.32
    POSITIVE LOGITS
     crime
    2.30
    crime
    2.02
     Crime
    2.00
    Crime
    1.99
     преступ
    1.76
    犯罪
    1.75
     अपराध
    1.68
     crimes
    1.63
     Crimes
    1.61
     क्राइम
    1.54
    Activations Density 0.000%

    No Known Activations