© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149910
    Prev
    Next
    INDEX
    Explanations

    company suffix

    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_23_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
     co
    0.46
    a
    0.42
    コ
    0.41
     decision
    0.41
       
    0.40
     demand
    0.40
     Senior
    0.40
     Veterans
    0.40
     TripAdvisor
    0.39
    /
    0.39
    POSITIVE LOGITS
    EditDialogOpen
    0.45
     তিনটা
    0.43
    não
    0.41
     thấy
    0.41
     प्रकारे
    0.40
     fuese
    0.40
     usados
    0.39
    ហា
    0.39
     nhá
    0.39
    tBleStatus
    0.39
    Activations Density 0.000%

    No Known Activations