© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38570
    Prev
    Next
    INDEX
    Explanations

    questions or requests

    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_57_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
     unto
    0.44
    到一个
    0.44
     thereto
    0.43
     agli
    0.41
     στους
    0.40
    ToObject
    0.39
    骢
    0.38
    ToIndex
    0.36
    Ai
    0.36
    ポスト
    0.35
    POSITIVE LOGITS
     به
    1.47
     à
    1.28
    به
    1.11
     Kep
    1.06
     aan
    1.05
    kep
    0.98
     kep
    0.95
    Kep
    0.86
    à
    0.85
     À
    0.84
    Activations Density 0.097%

    No Known Activations