© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 67577
    Prev
    Next
    INDEX
    Explanations

    symbols

    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
     single
    1.84
     Single
    1.75
    single
    1.74
    Single
    1.73
    单
    1.73
     SINGLE
    1.56
    SINGLE
    1.53
    單
    1.52
     одно
    1.49
     सिंगल
    1.45
    POSITIVE LOGITS
     og
    0.37
     عادی
    0.36
    ान्
    0.35
    㚼
    0.35
    काल
    0.34
     aus
    0.33
     objects
    0.33
     Ikat
    0.33
    ﮈ
    0.33
     いく
    0.33
    Activations Density 0.002%

    No Known Activations