© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85541
    Prev
    Next
    INDEX
    Explanations

    territory

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    る
    0.86
    ır
    0.84
    ار
    0.82
    lara
    0.82
    larda
    0.81
    l
    0.81
    ت
    0.81
    ри
    0.79
    ان
    0.77
    lari
    0.76
    POSITIVE LOGITS
    (
    0.64
    ，
    0.61
     sympath
    0.58
    、
    0.58
     procl
    0.57
     garanti
    0.57
     hvilket
    0.56
    没有
    0.56
     بواسطة
    0.55
     lequel
    0.55
    Activations Density 0.000%

    No Known Activations