© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165380
    Prev
    Next
    INDEX
    Explanations

    app =

    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_31_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
    Geb
    0.38
    罐
    0.37
    └
    0.37
    Draw
    0.36
     draw
    0.36
     উত্থ
    0.36
    чени
    0.36
     glm
    0.35
     스프
    0.34
    draw
    0.34
    POSITIVE LOGITS
     Turks
    0.39
    巡
    0.39
     Pat
    0.37
     Patrol
    0.37
     Garuda
    0.37
     Dang
    0.36
     Comm
    0.36
     emergencia
    0.35
     Krista
    0.34
     Plac
    0.34
    Activations Density 0.000%

    No Known Activations