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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124930
    Prev
    Next
    INDEX
    Explanations

    Billy Budd, Ray, Hoy

    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_3_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
    ل
    1.08
    ر
    0.90
     khỏe
    0.73
    л
    0.72
    لية
    0.71
    ０
    0.71
    б
    0.71
    0
    0.68
    ς
    0.68
    𝟎
    0.67
    POSITIVE LOGITS
    tor
    0.76
    de
    0.71
    in
    0.70
    ting
    0.70
    री
    0.70
    ている
    0.68
    ter
    0.68
    sl
    0.68
    ty
    0.66
    helf
    0.66
    Activations Density 0.000%

    No Known Activations