© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67368
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_41_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
     tails
    0.47
     tail
    0.42
    ிலான
    0.40
     rushed
    0.39
     tailed
    0.39
    ज्योति
    0.39
    odil
    0.38
    尾
    0.38
    ایل
    0.37
     Flaming
    0.37
    POSITIVE LOGITS
    ಷ್ಠ
    0.41
     acronym
    0.39
    휋
    0.39
    ክር
    0.39
    Соцмережа
    0.38
    ကြီး
    0.37
     macron
    0.37
    螞
    0.37
     मक
    0.37
    AKES
    0.37
    Activations Density 0.000%

    No Known Activations