© 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
    2. Gemma-3-27B-IT
    3. 0-GEMMASCOPE-2-TRANSCODER-262K
    4. 142026
    Prev
    Next
    INDEX
    Explanations

    살아 움직, 思考, 实时

    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
    is
    1.91
    on
    1.88
    م
    1.71
    z
    1.70
    has
    1.61
    to
    1.57
    '
    1.55
    ah
    1.55
    ia
    1.51
    ش
    1.48
    POSITIVE LOGITS
    arın
    1.40
    ।
    1.40
    arı
    1.38
    ară
    1.33
    ओं
    1.31
     garnished
    1.30
    놁
    1.30
     راجسټریشن
    1.26
     choreographed
    1.24
    ита
    1.23
    Activations Density 0.000%

    No Known Activations