© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15136
    Prev
    Next
    INDEX
    Explanations

    Gherkin, code, services, definition

    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_13_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
     вос
    0.46
     Milch
    0.45
     supervising
    0.45
    泠
    0.45
     जौ
    0.44
     Counseling
    0.44
     Crac
    0.43
    யா
    0.43
     Salman
    0.43
     instytuc
    0.43
    POSITIVE LOGITS
    وتی
    0.51
    variant
    0.49
    타
    0.49
    used
    0.48
    étaient
    0.47
    ètent
    0.47
    deviation
    0.47
    ма
    0.46
    前の
    0.46
    ორის
    0.46
    Activations Density 0.061%

    No Known Activations