© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13473
    Prev
    Next
    INDEX
    Explanations

    style, presentation, delivery

    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_13_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
    m
    0.46
    MIT
    0.42
    می
    0.42
    f
    0.41
    Te
    0.41
    TE
    0.40
    Module
    0.40
    redit
    0.40
    UN
    0.39
     c
    0.39
    POSITIVE LOGITS
     τύ
    0.40
     পৃষ্ঠ
    0.38
     ಸುತ್ತ
    0.37
    leqq
    0.37
     zust
    0.37
    噤
    0.37
    ෙස
    0.36
     Publikum
    0.36
    ੱਖ
    0.36
     décrire
    0.36
    Activations Density 0.167%

    No Known Activations