© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220871
    Prev
    Next
    INDEX
    Explanations

    avoid harsh soaps, lotions, or creams

    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
     ডিজিটাল
    0.34
     안전
    0.34
    ោក
    0.34
    埇
    0.34
     urethra
    0.32
    ствима
    0.32
     škola
    0.31
    牵
    0.31
    idação
    0.31
     Roshelle
    0.31
    POSITIVE LOGITS
     Flemish
    0.36
     composition
    0.35
     sprays
    0.34
    ular
    0.32
     gin
    0.32
     unnamed
    0.32
     denn
    0.31
     gins
    0.31
     verses
    0.31
     Composition
    0.31
    Activations Density 0.003%

    No Known Activations