© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159463
    Prev
    Next
    INDEX
    Explanations

    disenfranchisement, enlargement

    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
    to
    1.95
    the
    1.45
    in
    1.40
    k
    1.33
    ،
    1.30
    ，
    1.25
    し
    1.23
    ton
    1.22
    ty
    1.20
    test
    1.19
    POSITIVE LOGITS
    '
    1.53
    ли
    1.52
    .
    1.10
    едера
    1.01
    вет
    0.98
     تنظيم
    0.98
    ounds
    0.97
    то
    0.94
    '";
    0.93
     شرطونو
    0.91
    Activations Density 0.000%

    No Known Activations