© 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. 141855
    Prev
    Next
    INDEX
    Explanations

    彼 (he/his/their), красо (beauty), Aleppo

    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
    ку
    1.32
    全球
    1.19
    ปี
    1.15
    эль
    1.15
    他的
    1.14
    즌
    1.11
    정이
    1.09
    會有
    1.08
    를
    1.08
    fad
    1.07
    POSITIVE LOGITS
     for
    1.88
    ing
    1.77
    be
    1.44
    '
    1.44
    for
    1.41
    n
    1.40
    a
    1.38
    ер
    1.35
    />
    1.33
    त
    1.30
    Activations Density 0.000%

    No Known Activations