© 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. 142145
    Prev
    Next
    INDEX
    Explanations

    siphon and liquids

    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
     in
    1.97
     I
    1.73
    Я
    1.52
    t
    1.45
    ה
    1.39
    ใน
    1.37
    IB
    1.34
    在
    1.29
    Т
    1.27
    การ
    1.23
    POSITIVE LOGITS
    are
    1.84
    for
    1.70
    ut
    1.47
    or
    1.31
    ap
    1.30
    and
    1.29
    as
    1.27
    m
    1.27
     chinois
    1.26
    is
    1.20
    Activations Density 0.000%

    No Known Activations