© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117385
    Prev
    Next
    INDEX
    Explanations

    a significant percentage

    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_27_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
     قدیم
    0.36
     Mystery
    0.35
     alternation
    0.35
    yj
    0.34
     Conley
    0.34
     wechseln
    0.34
     가는
    0.34
    旧
    0.34
     erstwhile
    0.34
     gamle
    0.33
    POSITIVE LOGITS
    liš
    0.39
    innov
    0.39
     innov
    0.38
    𝙣
    0.37
    处置
    0.36
    already
    0.36
     impoz
    0.35
     demais
    0.35
     ваши
    0.34
    anjing
    0.34
    Activations Density 0.003%

    No Known Activations