© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124716
    Prev
    Next
    INDEX
    Explanations

    Geoffrey Hinton and Fortran code

    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_3_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
    ’
    1.06
    '
    0.68
    লে
    0.66
    )’
    0.64
     և
    0.61
     ότι
    0.58
    ರ್‌
    0.57
     明
    0.55
     Είναι
    0.55
    awać
    0.55
    POSITIVE LOGITS
    x
    1.05
     on
    1.03
    v
    0.95
    s
    0.89
    ت
    0.80
    c
    0.78
     for
    0.77
    u
    0.77
     at
    0.73
    b
    0.72
    Activations Density 0.008%

    No Known Activations