© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45273
    Prev
    Next
    INDEX
    Explanations

    code execution context

    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_10_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
    ación
    0.54
    incón
    0.52
    ↵
    0.51
    एस
    0.50
    ب
    0.50
    ně
    0.49
    ório
    0.49
    u
    0.49
    ção
    0.49
    ző
    0.48
    POSITIVE LOGITS
     can
    0.58
    0.48
    р
    0.48
    _
    0.47
    ',
    0.45
    }.
    0.43
     C
    0.40
     towel
    0.40
     DON
    0.40
    。
    0.40
    Activations Density 0.073%

    No Known Activations