© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103782
    Prev
    Next
    INDEX
    Explanations

    chocolatey

    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_1_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
    та
    1.32
    é
    0.97
    ية
    0.96
    يد
    0.93
    ين
    0.93
    ли
    0.91
     وي
    0.91
    но
    0.86
    يه
    0.86
    ן
    0.86
    POSITIVE LOGITS
    \
    1.12
    し
    1.11
    '
    1.05
    S
    1.03
    Y
    0.96
    おしゃれ
    0.95
    ’
    0.95
     katva
    0.92
    ש
    0.88
    د
    0.88
    Activations Density 0.001%

    No Known Activations