© 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. 204737
    Prev
    Next
    INDEX
    Explanations

    stories

    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
    n
    1.10
    re
    0.92
    ek
    0.91
    '
    0.87
    <0x0D>
    0.86
    nson
    0.84
     stints
    0.84
    ih
    0.82
    v
    0.82
    0.79
    POSITIVE LOGITS
     faucet
    0.73
    літы
    0.73
     drain
    0.71
    ल्ल्या
    0.70
    ல்
    0.69
     tour
    0.69
    фера
    0.69
    Lun
    0.69
    াং
    0.69
     pipe
    0.68
    Activations Density 0.002%

    No Known Activations