© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254015
    Prev
    Next
    INDEX
    Explanations

    CSRF protection

    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_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     partea
    0.37
    کنند
    0.37
    ದಲ್ಲ
    0.37
    ージェ
    0.35
    橋
    0.35
    mino
    0.35
    inz
    0.34
    etheus
    0.34
    Ow
    0.33
    ereco
    0.33
    POSITIVE LOGITS
     أص
    0.37
     précie
    0.37
     своему
    0.37
    ど
    0.37
     fileCopy
    0.36
     Oaks
    0.35
     Wide
    0.34
    SLASH
    0.34
     שי
    0.34
     과
    0.33
    Activations Density 0.003%

    No Known Activations