© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216541
    Prev
    Next
    INDEX
    Explanations

    code script 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_31_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
    ACION
    0.36
     אור
    0.36
    Hot
    0.35
     Hendricks
    0.34
    rypt
    0.34
    埋
    0.34
     McLean
    0.33
    等等
    0.33
     calculations
    0.33
    ánicas
    0.33
    POSITIVE LOGITS
     ആരോ
    0.40
    ophyte
    0.39
     पारस्परिक
    0.39
    ');//
    0.37
     سطح
    0.37
    ંપની
    0.37
     nível
    0.36
     Either
    0.35
     hypogly
    0.35
     contro
    0.35
    Activations Density 0.000%

    No Known Activations