© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 224709
    Prev
    Next
    INDEX
    Explanations

    copilot, copra, copium, copay, copernicus, copbio, cops

    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
    ’
    0.63
     wagon
    0.59
     wag
    0.59
     by
    0.55
     part
    0.54
     water
    0.54
     vode
    0.53
     in
    0.53
     five
    0.53
    '
    0.52
    POSITIVE LOGITS
    ov
    0.93
    ي
    0.79
    teste
    0.78
    на
    0.75
    ap
    0.74
    uo
    0.74
    il
    0.73
    ın
    0.72
    im
    0.72
    son
    0.71
    Activations Density 0.002%

    No Known Activations