© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 151214
    Prev
    Next
    INDEX
    Explanations

    css cursor pointer

    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_23_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
    ‶
    0.46
     selepas
    0.42
     soviet
    0.42
     “(
    0.39
    eningrad
    0.39
     mata
    0.38
    esempio
    0.38
    ɐ
    0.37
     hauled
    0.37
    “(
    0.37
    POSITIVE LOGITS
     Winn
    0.43
     tắc
    0.39
    のもの
    0.39
    แต่ละ
    0.38
     என்னுடைய
    0.37
     मुख्य
    0.36
    的主要
    0.36
    の詳細
    0.35
    Pinterest
    0.35
    物
    0.35
    Activations Density 0.001%

    No Known Activations