© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30022
    Prev
    Next
    INDEX
    Explanations

    interview or test questions

    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_7_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
    ре
    0.30
    و
    0.29
    ла
    0.28
    िशन
    0.28
    ه‌
    0.27
    。「
    0.26
    لة
    0.26
    дий
    0.26
    гора
    0.26
    да
    0.25
    POSITIVE LOGITS
    is
    0.43
    ic
    0.41
    at
    0.41
    ed
    0.39
    and
    0.38
    as
    0.37
    id
    0.37
    k
    0.36
    es
    0.36
    ra
    0.36
    Activations Density 0.007%

    No Known Activations