© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 202509
    Prev
    Next
    INDEX
    Explanations

    variable assignment and code structure

    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_37_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
    хин
    0.41
    ㄷ
    0.39
    ोरेंट
    0.39
     Motions
    0.38
     createArticle
    0.38
     rì
    0.38
     É
    0.37
     ñ
    0.36
     лу
    0.35
     minSdkVersion
    0.35
    POSITIVE LOGITS
    RP
    0.40
    straat
    0.39
    scalar
    0.38
    DUT
    0.37
    ar
    0.36
    ammad
    0.36
    ickey
    0.36
    getic
    0.36
    ___
    0.35
     $=
    0.35
    Activations Density 0.030%

    No Known Activations