© 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. 142413
    Prev
    Next
    INDEX
    Explanations

    modelmodel definition or context

    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
    網
    0.59
    حديث
    0.58
     الالكتر
    0.58
    تمر
    0.57
    Lors
    0.55
    Authenticator
    0.54
    Coin
    0.53
    Shr
    0.53
    ᆭ
    0.53
    গঞ্জ
    0.52
    POSITIVE LOGITS
    ocard
    0.62
     tujuh
    0.59
    -
    0.58
    os
    0.57
    oping
    0.55
    ović
    0.55
    lera
    0.55
    alid
    0.53
    tt
    0.52
    ları
    0.52
    Activations Density 0.000%

    No Known Activations