© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173784
    Prev
    Next
    INDEX
    Explanations

    listing examples or actions

    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
     tutte
    0.42
    ा
    0.42
    two
    0.40
     सारी
    0.39
    zł
    0.39
     dozens
    0.39
     zwei
    0.39
     two
    0.39
    sparse
    0.39
     equivariant
    0.38
    POSITIVE LOGITS
    โร
    0.45
    ஜ
    0.41
    SOA
    0.41
     Doh
    0.40
    EnglishMarks
    0.39
     )
    0.38
    гия
    0.38
     SOA
    0.38
     Sonora
    0.38
    കി
    0.37
    Activations Density 0.004%

    No Known Activations