© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18968
    Prev
    Next
    INDEX
    Explanations

    wikipedia links

    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_40_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
     Script
    0.38
     steep
    0.38
     villa
    0.37
    checking
    0.36
     ইরান
    0.36
     villas
    0.36
     submission
    0.36
    終
    0.36
    submission
    0.35
     erricht
    0.35
    POSITIVE LOGITS
     nav
    0.45
    blox
    0.43
    樣
    0.41
    Nav
    0.40
     Nav
    0.40
    дото
    0.38
    nav
    0.38
     navigational
    0.38
     линей
    0.38
    orical
    0.37
    Activations Density 0.004%

    No Known Activations