© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90945
    Prev
    Next
    INDEX
    Explanations

    ic

    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_11_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
    p
    0.84
    in
    0.79
    4
    0.71
    akan
    0.69
    _
    0.68
    6
    0.67
    urang
    0.65
    (
    0.65
    inya
    0.64
    3
    0.63
    POSITIVE LOGITS
     cuddling
    0.61
     chern
    0.60
    𝘣
    0.59
     cuddle
    0.59
     mett
    0.58
    𝘯
    0.58
    ри
    0.57
     multitude
    0.55
     cashmere
    0.55
    记住
    0.54
    Activations Density 0.003%

    No Known Activations