© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171352
    Prev
    Next
    INDEX
    Explanations

    listening on port

    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_20_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
    do
    0.46
     ۴
    0.46
    ۴
    0.46
     protéines
    0.43
    ܢܐ
    0.42
    ﮄ
    0.42
    烪
    0.41
    軞
    0.40
     ૨
    0.40
     venant
    0.40
    POSITIVE LOGITS
     Mahoney
    0.41
     Chand
    0.39
     खान
    0.38
     Council
    0.38
    萧
    0.38
     Walden
    0.38
     Maxwell
    0.37
    Travis
    0.37
     नी
    0.37
     Carlson
    0.37
    Activations Density 0.002%

    No Known Activations