© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54512
    Prev
    Next
    INDEX
    Explanations

    criminal

    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_55_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
    뿌
    0.40
    টায়
    0.37
    ுகிறது
    0.37
     뿌
    0.36
    津
    0.35
    ს
    0.34
    CY
    0.34
    ging
    0.34
     머
    0.34
    블릿
    0.34
    POSITIVE LOGITS
     criminal
    1.27
     Criminal
    1.12
    criminal
    1.11
    Criminal
    1.04
     CRIMINAL
    1.03
     आपराधिक
    0.75
     уголов
    0.71
     kriminal
    0.66
    刑事
    0.64
     criminality
    0.63
    Activations Density 0.017%

    No Known Activations