© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129274
    Prev
    Next
    INDEX
    Explanations

    SPARQL query

    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
    ب
    1.24
    ’
    1.16
    我
    1.13
    {
    1.07
    پ
    1.03
    ކ
    1.03
     indiquer
    1.02
    ographies
    1.01
     ότι
    0.99
    Các
    0.97
    POSITIVE LOGITS
    ен
    0.97
     church
    0.95
    ﺪ
    0.94
     soirée
    0.91
    ים
    0.90
     c
    0.89
     porch
    0.87
     z
    0.86
    важа
    0.86
     line
    0.84
    Activations Density 0.000%

    No Known Activations