© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 522
    Prev
    Next
    INDEX
    Explanations

    technical code

    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_44_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
    hauser
    0.13
    ივ
    0.13
    )--
    0.13
    作为一个
    0.13
    ﺮ
    0.13
     carreteras
    0.13
     регуляр
    0.12
    해도
    0.12
     Yuc
    0.12
    ország
    0.12
    POSITIVE LOGITS
     mdl
    0.15
    дентифика
    0.15
    Papa
    0.14
    ⠈
    0.14
    apad
    0.14
    ranial
    0.14
    ាតុ
    0.14
    丙
    0.14
    ocratic
    0.14
     pepe
    0.14
    Activations Density 0.179%

    No Known Activations