© 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. 43916
    Prev
    Next
    INDEX
    Explanations

    Hasegawa, Factory, code, program

    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
    o
    1.11
    d
    1.05
    as
    0.95
    in
    0.93
    en
    0.89
    u
    0.86
    ana
    0.80
    ing
    0.79
    g
    0.77
    anaa
    0.77
    POSITIVE LOGITS
     for
    0.75
     لأ
    0.68
     Até
    0.68
    Js
    0.66
    ۰
    0.66
    0
    0.64
     الر
    0.63
    Α
    0.63
    OP
    0.62
     والاست
    0.62
    Activations Density 0.014%

    No Known Activations