© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43962
    Prev
    Next
    INDEX
    Explanations

    greentext

    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_13_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
     Vegetarian
    0.32
     Políticas
    0.30
    ?")
    0.30
    ील
    0.30
    vegetarian
    0.29
    楹
    0.29
    ”)
    0.28
     vegetarian
    0.27
     botón
    0.27
    ாயம்
    0.27
    POSITIVE LOGITS
    l
    0.33
    6
    0.31
     subunits
    0.31
     juste
    0.31
     aquesta
    0.30
    لي
    0.30
    لہ
    0.29
     pracuje
    0.29
     arbete
    0.28
     complexes
    0.28
    Activations Density 0.011%

    No Known Activations