© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170730
    Prev
    Next
    INDEX
    Explanations

    do you like

    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_20_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
    سات
    0.42
     ٿ
    0.39
     नॉट
    0.38
    тяну
    0.38
    啬
    0.38
    玤
    0.38
    開心
    0.38
    ENCED
    0.38
     будете
    0.37
    少
    0.37
    POSITIVE LOGITS
     governorship
    0.46
     elem
    0.46
     оружия
    0.45
    miller
    0.44
     conjectured
    0.43
     proprietary
    0.42
     doing
    0.42
     nightmare
    0.42
     Mene
    0.42
     fala
    0.41
    Activations Density 0.003%

    No Known Activations