© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45931
    Prev
    Next
    INDEX
    Explanations

    PUBG editions

    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_13_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
    as
    0.59
     as
    0.52
    %.
    0.46
    鹼
    0.46
     ProductCategory
    0.45
    一
    0.45
    因為
    0.45
     Compiled
    0.45
    o
    0.45
    in
    0.45
    POSITIVE LOGITS
     arası
    0.52
     prok
    0.47
     disenfranch
    0.46
     plaatsen
    0.45
    otype
    0.45
    जनक
    0.45
     حق
    0.45
     दीवार
    0.44
     دیگر
    0.43
     поко
    0.43
    Activations Density 0.007%

    No Known Activations