© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200945
    Prev
    Next
    INDEX
    Explanations

    v

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    បុ
    0.39
    ódigo
    0.37
     }}$,
    0.36
    BUND
    0.36
    ELDS
    0.35
    дії
    0.35
    ড়ে
    0.35
    헤
    0.35
    Aes
    0.34
    ല്ല
    0.34
    POSITIVE LOGITS
    ppage
    0.47
     ial
    0.44
     Eton
    0.42
    bibinfo
    0.40
     ار
    0.39
    opyran
    0.38
    arif
    0.38
     luas
    0.38
    ለኛ
    0.37
     Encyclopedia
    0.37
    Activations Density 0.002%

    No Known Activations