© 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. 195435
    Prev
    Next
    INDEX
    Explanations

    say "a" words

    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
    рит
    0.42
    习近平
    0.39
    Adobe
    0.38
    Eco
    0.37
    鉑
    0.36
     walked
    0.35
    ධා
    0.35
    oxa
    0.35
     Adobe
    0.34
    '].'
    0.34
    POSITIVE LOGITS
     Io
    0.44
     Ін
    0.42
     Ио
    0.39
    ുടെ
    0.38
     Dan
    0.38
    ตัน
    0.38
     mí
    0.38
    udes
    0.38
    マジ
    0.38
     Rang
    0.37
    Activations Density 0.001%

    No Known Activations