© 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. 8841
    Prev
    Next
    INDEX
    Explanations

    API components/schemas

    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
     स्नान
    0.37
     poiché
    0.34
    િટ
    0.33
     sucedió
    0.32
     זו
    0.32
     ważne
    0.32
     ṣ
    0.31
     modificación
    0.31
     ši
    0.31
     čo
    0.31
    POSITIVE LOGITS
     org
    0.32
    (
    0.32
    academia
    0.31
    im
    0.31
    temp
    0.31
    ’
    0.31
    \[
    0.30
    timeout
    0.30
    index
    0.29
    me
    0.29
    Activations Density 0.011%

    No Known Activations