© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111666
    Prev
    Next
    INDEX
    Explanations

    ikas, iker, ikar, antol, antz, zilar

    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_2_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
    ل
    1.59
    জ
    1.39
    он
    1.34
    Б
    1.31
    מ
    1.30
    נ
    1.21
    ك
    1.17
    ра
    1.16
    ্যা
    1.15
    פ
    1.15
    POSITIVE LOGITS
    o
    1.21
    (
    1.09
    y
    0.97
    s
    0.95
    u
    0.94
    oin
    0.94
    ad
    0.93
    ität
    0.91
    iv
    0.89
    atio
    0.88
    Activations Density 0.001%

    No Known Activations