© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15002
    Prev
    Next
    INDEX
    Explanations

    dates and conferences

    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_13_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
    ik
    0.38
    uk
    0.38
     \
    0.33
     Με
    0.33
    st
    0.32
     */
    0.31
    шы
    0.31
     Efect
    0.31
     Booker
    0.30
     Asher
    0.30
    POSITIVE LOGITS
     defining
    0.35
     esclare
    0.35
    definition
    0.33
    ње
    0.33
     определение
    0.33
     lymph
    0.33
    ȇ
    0.33
    ನ್ನು
    0.32
     sulla
    0.32
    ację
    0.32
    Activations Density 0.006%

    No Known Activations