© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154965
    Prev
    Next
    INDEX
    Explanations

    game items characters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     REPLY
    0.46
    leqq
    0.42
     Rewrite
    0.41
    Rewrite
    0.41
    諒
    0.41
    La
    0.38
    Um
    0.38
    ریض
    0.38
     Missy
    0.38
    ಉ
    0.38
    POSITIVE LOGITS
     Chloride
    0.38
     zen
    0.37
     플
    0.37
    辅
    0.37
    的国家
    0.37
     जस
    0.36
    arsenic
    0.36
     spie
    0.36
     كله
    0.36
     dese
    0.35
    Activations Density 0.000%

    No Known Activations