© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208125
    Prev
    Next
    INDEX
    Explanations

    " ABC'

    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_20_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
    vdd
    0.42
    svg
    0.42
     electrode
    0.42
    नहीं
    0.42
     Electrode
    0.41
     Ecommerce
    0.41
    prone
    0.40
    <unused37>
    0.40
     También
    0.40
    electrode
    0.40
    POSITIVE LOGITS
     resurrected
    0.47
     cucumber
    0.44
     прадстаў
    0.42
     cucumbers
    0.41
     кін
    0.41
     ск
    0.40
     resurgence
    0.40
    irs
    0.40
    چر
    0.39
    ку
    0.38
    Activations Density 0.025%

    No Known Activations