© 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. 132704
    Prev
    Next
    INDEX
    Explanations

    renewable energy

    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
     tro
    0.41
    σκε
    0.38
     சிவ
    0.37
     kua
    0.36
    ைகள்
    0.36
     adi
    0.36
    恈
    0.36
    מות
    0.36
     металли
    0.36
     radix
    0.36
    POSITIVE LOGITS
    azgo
    0.45
    ிக
    0.39
    Vill
    0.39
     এজ
    0.39
     punti
    0.38
    <html>
    0.38
     Villeneuve
    0.37
    agan
    0.37
    Dp
    0.37
    Hfn
    0.37
    Activations Density 0.000%

    No Known Activations