© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62777
    Prev
    Next
    INDEX
    Explanations

    tuk-tuks

    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
    Negative Logits
    is
    1.61
    a
    1.27
    on
    1.19
    ie
    1.14
    ه
    1.14
    ik
    1.06
    il
    1.03
    ب
    1.02
    ah
    0.98
    ian
    0.97
    POSITIVE LOGITS
    to
    1.73
     to
    1.41
    し
    1.19
    য়
    1.10
    ش
    1.03
    кий
    1.01
    toare
    1.01
    tainment
    1.00
    ting
    1.00
    یکه
    0.99
    Activations Density 0.003%

    No Known Activations