© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41388
    Prev
    Next
    INDEX
    Explanations

    useEffect hook

    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_22_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
     magnitude
    0.43
    겠지만
    0.43
     feasibility
    0.41
     रिश्तेदारों
    0.41
     fea
    0.40
    !।
    0.39
     买
    0.39
    ał
    0.38
    लाइजेशन
    0.38
     /><
    0.38
    POSITIVE LOGITS
    слей
    0.40
    KYO
    0.40
     Acres
    0.39
    стта
    0.39
     Niko
    0.38
    Omar
    0.38
    שת
    0.38
     acres
    0.38
    Secrets
    0.38
    Obl
    0.38
    Activations Density 0.000%

    No Known Activations