© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50722
    Prev
    Next
    INDEX
    Explanations

    direct & professional

    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_31_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
     मारपीट
    0.75
    骂
    0.73
     violent
    0.68
     punishment
    0.66
    罵
    0.66
    殴
    0.65
    暴力
    0.64
    揍
    0.63
    violent
    0.62
    멱
    0.62
    POSITIVE LOGITS
     pg
    0.40
     ship
    0.38
     colonization
    0.38
     transparent
    0.37
     emigration
    0.36
     نوا
    0.35
     bypassed
    0.35
    辇
    0.35
     bypass
    0.35
     Dela
    0.35
    Activations Density 0.056%

    No Known Activations