© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15227
    Prev
    Next
    INDEX
    Explanations

    Let's break down

    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
     say
    0.86
    say
    0.75
    Say
    0.73
     Say
    0.69
     digamos
    0.66
     sagen
    0.63
     decir
    0.59
    说
    0.54
    說是
    0.51
    说是
    0.48
    POSITIVE LOGITS
     покри
    0.54
     покрытие
    0.52
     COVER
    0.49
     covered
    0.48
    COVER
    0.47
     покрытия
    0.46
     covers
    0.45
     covering
    0.45
     cover
    0.44
    cover
    0.42
    Activations Density 0.045%

    No Known Activations