© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48174
    Prev
    Next
    INDEX
    Explanations

    sun

    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_10_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
     of
    0.39
    t
    0.33
    tım
    0.31
     spikes
    0.29
     on
    0.29
     tentacles
    0.28
          
    0.28
     yards
    0.27
    ación
    0.27
     wires
    0.27
    POSITIVE LOGITS
    G
    0.33
    U
    0.31
    OO
    0.30
    IA
    0.29
    Estas
    0.29
    archiw
    0.29
    Photography
    0.28
    OP
    0.28
    Which
    0.28
    B
    0.28
    Activations Density 0.018%

    No Known Activations