© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166641
    Prev
    Next
    INDEX
    Explanations

    and

    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_31_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
     intravenously
    0.41
    ருடன்
    0.38
     notar
    0.38
     powerhouse
    0.37
    娑
    0.36
     المنزل
    0.36
     entrust
    0.36
     dynamism
    0.35
     nol
    0.35
     leukemia
    0.35
    POSITIVE LOGITS
     revision
    0.42
    ziale
    0.38
     furent
    0.37
     Revision
    0.36
     অনেকটা
    0.36
    郆
    0.36
    ibilités
    0.36
    審
    0.36
    revision
    0.35
    anoi
    0.35
    Activations Density 0.003%

    No Known Activations