© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24508
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation

    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_56_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
    hende
    0.38
     সুইচ
    0.35
     வேத
    0.31
     پلا
    0.31
    醗
    0.31
    鍱
    0.31
     হাতের
    0.31
     보겠습니다
    0.31
    ንን
    0.31
     अटक
    0.31
    POSITIVE LOGITS
    ٫
    0.60
    {,}
    0.54
     डॉट
    0.43
    .$,
    0.43
    ()")
    0.41
    .%
    0.41
    ½
    0.40
    @
    0.39
    닷
    0.39
     com
    0.38
    Activations Density 0.137%

    No Known Activations