© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108374
    Prev
    Next
    INDEX
    Explanations

    again, followed by punctuation

    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_1_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
    л
    1.22
    1
    1.08
    д
    0.98
    ль
    0.96
    3
    0.93
     of
    0.92
    ком
    0.90
    src
    0.90
    كل
    0.86
    smittel
    0.86
    POSITIVE LOGITS
    UT
    0.82
    نا
    0.80
     in
    0.77
    도
    0.76
    ’
    0.75
    ও
    0.75
     ذریع
    0.73
    ాన్ని
    0.72
    ่
    0.70
    ח
    0.70
    Activations Density 0.001%

    No Known Activations