© 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. 41319
    Prev
    Next
    INDEX
    Explanations

    hardly followed by qualifiers

    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
    ↵
    0.69
    d
    0.68
    7
    0.66
    g
    0.64
     to
    0.63
    to
    0.61
    b
    0.61
    8
    0.60
    n
    0.59
    6
    0.57
    POSITIVE LOGITS
     vuccati
    0.60
     Итали
    0.59
    ンの
    0.58
     Ukraj
    0.58
    ри
    0.57
     calific
    0.57
    achron
    0.56
    тера
    0.55
    чно
    0.55
    atthena
    0.55
    Activations Density 0.000%

    No Known Activations