© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 78081
    Prev
    Next
    INDEX
    Explanations

    Ethical statement justification

    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
    套装
    0.39
    Cliff
    0.37
    rensa
    0.37
    ">=</
    0.37
     Coliseum
    0.36
     सर्जन
    0.36
     लंबित
    0.35
     vann
    0.35
    展示
    0.34
    genre
    0.34
    POSITIVE LOGITS
    ylsulfanyl
    0.39
     Worcestershire
    0.38
     <=
    0.37
    ផល
    0.36
    pecies
    0.36
     அச
    0.35
     minimal
    0.35
     larval
    0.35
     apl
    0.34
    opio
    0.34
    Activations Density 0.000%

    No Known Activations