© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202735
    Prev
    Next
    INDEX
    Explanations

    cic, cicada, cicchi, ciccone, cicatrix, ciclo

    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_6_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
    س
    1.39
    с
    1.16
    ал
    1.09
    е
    1.05
    ло
    1.05
    ي
    1.02
    о
    1.01
    ле
    0.95
    ص
    0.95
    าย
    0.91
    POSITIVE LOGITS
    3
    1.09
    ar
    0.94
     Gölü
    0.87
    in
    0.83
     with
    0.81
     komunitas
    0.80
    jev
    0.80
     Иң
    0.79
    cosim
    0.79
     Frontiers
    0.78
    Activations Density 0.000%

    No Known Activations