© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226604
    Prev
    Next
    INDEX
    Explanations

    canny edge detection

    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_10_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
    is
    0.84
    of
    0.70
    was
    0.61
    的关系
    0.61
    0
    0.59
    to
    0.58
    as
    0.57
    )$
    0.56
    Después
    0.55
    ER
    0.55
    POSITIVE LOGITS
     احترام
    0.61
     delicate
    0.58
     optimistic
    0.55
     prolific
    0.54
     bille
    0.53
    山口
    0.53
    ignac
    0.53
     КА
    0.53
     Anwar
    0.52
     abrasive
    0.52
    Activations Density 0.000%

    No Known Activations