© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201986
    Prev
    Next
    INDEX
    Explanations

    learn

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    haan
    0.41
    軛
    0.40
     Haft
    0.38
    viet
    0.38
    mett
    0.36
    нэт
    0.36
    虺
    0.36
     nhiễm
    0.35
     /[
    0.35
    🌖
    0.35
    POSITIVE LOGITS
     statistics
    1.38
    Statistics
    1.34
    statistics
    1.31
     Statistics
    1.30
    统计
    1.19
     STATISTICS
    1.11
    統計
    1.10
     statistical
    1.07
     statistiques
    1.04
    Statistical
    1.03
    Activations Density 0.006%

    No Known Activations