© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61202
    Prev
    Next
    INDEX
    Explanations

    namespace App

    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_11_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
     i
    0.60
    ia
    0.60
    ė
    0.59
    /
    0.57
    —
    0.57
    ley
    0.57
    ing
    0.55
     to
    0.55
    ING
    0.53
    rij
    0.53
    POSITIVE LOGITS
    汢
    0.59
    雰
    0.57
     شود
    0.57
    న్స్
    0.57
    都会
    0.56
    约束
    0.55
    多么
    0.54
     Hartree
    0.54
    ચર
    0.53
    творю
    0.53
    Activations Density 0.000%

    No Known Activations