© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123431
    Prev
    Next
    INDEX
    Explanations

    Executive Committee or Leadership

    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_3_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
     I
    0.69
     a
    0.57
    a
    0.55
    Def
    0.55
     enl
    0.54
    м
    0.52
    ane
    0.52
     Gó
    0.51
     Canva
    0.50
    vieve
    0.50
    POSITIVE LOGITS
    。</
    0.78
    ش
    0.71
    ダー
    0.69
    га
    0.68
     transistors
    0.66
    executed
    0.66
    。【
    0.64
    âteaux
    0.64
     transistor
    0.62
    実行
    0.62
    Activations Density 0.000%

    No Known Activations