© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156507
    Prev
    Next
    INDEX
    Explanations

    HOG Descriptor or Hough Lines

    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_2_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
    t
    2.25
    en
    1.77
    an
    1.69
    y
    1.66
    2
    1.64
    f
    1.63
    de
    1.61
    z
    1.61
    te
    1.59
    re
    1.58
    POSITIVE LOGITS
     bună
    0.96
     consultez
    0.93
    0.93
     أغسطس
    0.89
     zariaden
    0.89
     пор
    0.88
    েরা
    0.84
    いますが
    0.84
     οι
    0.84
    ාවිත
    0.84
    Activations Density 0.001%

    No Known Activations