© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202354
    Prev
    Next
    INDEX
    Explanations

    HTML elements following 'my'

    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_12_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
    ing
    0.83
    to
    0.69
    window
    0.66
    sw
    0.65
    Squirrel
    0.65
    c
    0.65
    sum
    0.64
    space
    0.64
    C
    0.63
    sq
    0.62
    POSITIVE LOGITS
     сер
    0.63
     intrepid
    0.59
     mù
    0.59
     exorbit
    0.57
     naïve
    0.57
     видом
    0.57
     yù
    0.57
     fornisce
    0.55
    鱈
    0.55
     різ
    0.54
    Activations Density 0.000%

    No Known Activations