© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148339
    Prev
    Next
    INDEX
    Explanations

    duration, scope, or purpose

    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_23_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
    ካከል
    0.39
     Bela
    0.38
    atinib
    0.38
    尽
    0.37
     forcing
    0.36
     PAM
    0.36
     probed
    0.36
    떻
    0.36
     extrap
    0.36
    昱
    0.36
    POSITIVE LOGITS
    isset
    0.39
    त्
    0.38
    uret
    0.38
    üssel
    0.36
     これ
    0.36
    Зна
    0.36
     entrando
    0.36
     कस
    0.35
    oses
    0.35
    зец
    0.35
    Activations Density 0.044%

    No Known Activations