© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84427
    Prev
    Next
    INDEX
    Explanations

    finely tune, adjust, or divide

    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_0_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
    انی
    1.31
    یر
    1.20
    ğini
    1.12
     начало
    1.11
    ক
    1.11
    یده
    1.09
     самое
    1.09
     cruel
    1.09
     elementów
    1.09
    ルコ
    1.08
    POSITIVE LOGITS
    a
    1.80
    w
    1.71
    that
    1.67
    r
    1.63
    ه
    1.59
    sp
    1.49
    n
    1.45
    an
    1.42
    l
    1.41
    ta
    1.40
    Activations Density 0.001%

    No Known Activations