© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259598
    Prev
    Next
    INDEX
    Explanations

    fill in blanks

    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_22_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
     тысяч
    0.39
    раз
    0.38
     также
    0.38
    氻
    0.37
     burial
    0.37
     toki
    0.37
     spectacularly
    0.36
     hours
    0.35
    тру
    0.35
    这才
    0.35
    POSITIVE LOGITS
    xcscheme
    0.41
     Peu
    0.40
    <0x89>
    0.39
    ifizierung
    0.39
    ibat
    0.38
    ಬೇಕ
    0.38
    pleo
    0.37
    ེད་
    0.37
    の使い方
    0.36
    ื
    0.36
    Activations Density 0.000%

    No Known Activations