© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122480
    Prev
    Next
    INDEX
    Explanations

    older brothers, sisters, siblings

    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_3_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
    al
    1.09
    ة
    1.07
    ב
    1.04
    ing
    1.02
    ле
    1.01
    은
    0.97
    िंग
    0.95
    ad
    0.89
    は
    0.89
    ü
    0.89
    POSITIVE LOGITS
    тку
    0.79
    𝙣
    0.76
    ELL
    0.73
    𝙞
    0.63
    gauge
    0.63
    STER
    0.62
    𝙡
    0.61
    IR
    0.60
    digit
    0.60
    draft
    0.59
    Activations Density 0.002%

    No Known Activations