© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202572
    Prev
    Next
    INDEX
    Explanations

    company names

    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_46_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
     palt
    0.39
     }^{-
    0.39
     सेंटी
    0.37
     zosta
    0.36
    サリー
    0.36
     vén
    0.36
     देन
    0.35
     OT
    0.35
     liệu
    0.35
    장을
    0.35
    POSITIVE LOGITS
    amientos
    0.38
    kath
    0.38
    ರೂ
    0.37
    casters
    0.37
     ስ
    0.36
    russ
    0.36
    ంగ్
    0.36
    タップ
    0.36
    aust
    0.36
    cat
    0.35
    Activations Density 0.008%

    No Known Activations