© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195517
    Prev
    Next
    INDEX
    Explanations

    count

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     vá
    0.53
     Vá
    0.41
    میل
    0.41
    वाद
    0.39
     வ
    0.38
     উপে
    0.38
    ﻊ
    0.38
     underline
    0.38
     V
    0.37
    addLine
    0.37
    POSITIVE LOGITS
     zap
    0.52
     poč
    0.52
     prih
    0.49
     zak
    0.46
    Tính
    0.45
    count
    0.45
    Zak
    0.43
     Count
    0.43
     count
    0.42
     Acceptance
    0.41
    Activations Density 0.002%

    No Known Activations