© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198183
    Prev
    Next
    INDEX
    Explanations

    job, Theft, Auto

    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_9_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
     for
    0.62
    方
    0.59
    фта
    0.55
    H
    0.55
    вейца
    0.54
    فر
    0.53
    我们
    0.53
     വീട്ട
    0.53
    হ্য
    0.52
    చ్చే
    0.52
    POSITIVE LOGITS
    ’
    0.63
     químicas
    0.59
     digits
    0.57
     pigments
    0.57
     degrees
    0.57
     monoxide
    0.57
     fleece
    0.56
     diodes
    0.56
     clothes
    0.55
     सम
    0.55
    Activations Density 0.000%

    No Known Activations