© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163596
    Prev
    Next
    INDEX
    Explanations

    ribbon

    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
    Not in Any Lists

    No Comments

    Negative Logits
     dereg
    0.14
    ܝ
    0.13
     allegedly
    0.13
     מע
    0.13
     sekal
    0.13
     appalling
    0.13
    يد
    0.13
    מש
    0.13
     steeply
    0.13
    ým
    0.13
    POSITIVE LOGITS
     There
    0.16
     Brochure
    0.14
    odynam
    0.13
    t
    0.13
    λία
    0.13
     Teeth
    0.13
    জিব
    0.12
    Karte
    0.12
     Cognito
    0.12
     It
    0.12
    Activations Density 0.003%

    No Known Activations