© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62775
    Prev
    Next
    INDEX
    Explanations

    vested interests

    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_11_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
     for
    0.79
    అ
    0.64
     pneus
    0.63
    <0x0D>
    0.61
     multe
    0.58
    You
    0.57
     otom
    0.57
    ア
    0.57
     ail
    0.56
    τ
    0.54
    POSITIVE LOGITS
    enia
    0.59
    remain
    0.58
    igger
    0.57
    rystall
    0.56
    ėje
    0.56
    setEnabled
    0.56
    groups
    0.54
    ্লোক
    0.54
    enk
    0.54
    ruč
    0.54
    Activations Density 0.000%

    No Known Activations