© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89227
    Prev
    Next
    INDEX
    Explanations

    Start

    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
    uğ
    0.43
     germ
    0.42
     요구
    0.39
     seva
    0.39
    тоў
    0.39
     Comparator
    0.37
     GERM
    0.37
    玴
    0.37
    вовано
    0.37
    相邻
    0.37
    POSITIVE LOGITS
    jane
    0.39
    irken
    0.37
    eng
    0.37
    ểm
    0.37
    bard
    0.36
     చిత
    0.35
    ==="
    0.35
    img
    0.35
    ir
    0.35
    endu
    0.35
    Activations Density 0.000%

    No Known Activations