© 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. 197843
    Prev
    Next
    INDEX
    Explanations

    center, inside, point, forward, driving

    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
    Negative Logits
     thay
    0.20
    INS
    0.19
    Log
    0.19
     xong
    0.19
    Ciao
    0.19
    light
    0.18
    .<
    0.18
    fläche
    0.18
    ✿
    0.18
    Logo
    0.18
    POSITIVE LOGITS
    prendre
    0.20
     бо
    0.19
     Dwarf
    0.19
     Sword
    0.19
     MILLER
    0.19
     कमाल
    0.18
     Malgré
    0.18
    яз
    0.18
     miserable
    0.18
     Yarm
    0.17
    Activations Density 0.000%

    No Known Activations