© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196423
    Prev
    Next
    INDEX
    Explanations

    imports and function calls (python)

    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
    Emily
    0.40
    Ǻ
    0.40
    Agree
    0.40
    Disagree
    0.39
    Fechar
    0.39
    Sant
    0.39
    например
    0.38
    ㄷ
    0.38
    锕
    0.38
     bijvoorbeeld
    0.38
    POSITIVE LOGITS
     ভাগে
    0.44
     பார்க்க
    0.40
    ourent
    0.39
     back
    0.39
     wear
    0.39
    មើល
    0.38
    鳎
    0.38
     رفع
    0.38
    bi
    0.37
    iane
    0.37
    Activations Density 0.005%

    No Known Activations