© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142266
    Prev
    Next
    INDEX
    Explanations

    point-to-point

    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_12_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
     MILLER
    0.20
     demise
    0.18
     glaring
    0.17
     underval
    0.17
     o
    0.16
     GLASS
    0.16
     table
    0.16
     decept
    0.16
     نصی
    0.16
     ج
    0.16
    POSITIVE LOGITS
     logotipo
    0.18
     ощущение
    0.17
    signUp
    0.17
     थोडे
    0.17
     ఉపయోగ
    0.17
    цвет
    0.16
     Erwachsene
    0.16
     पद्
    0.16
    ጨማሪ
    0.16
    ные
    0.16
    Activations Density 0.001%

    No Known Activations