© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45764
    Prev
    Next
    INDEX
    Explanations

    file formats and terms

    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_22_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
    Accept
    0.40
    础
    0.39
    Port
    0.39
    Play
    0.39
    А
    0.39
    ត់
    0.38
    Intent
    0.38
    Drivers
    0.38
    ཛ
    0.38
    Oh
    0.37
    POSITIVE LOGITS
    /
    1.00
     atau
    0.77
     किंवा
    0.75
     /
    0.74
    หรือ
    0.74
    或
    0.74
     또는
    0.74
     или
    0.73
     hoặc
    0.70
     alebo
    0.70
    Activations Density 0.069%

    No Known Activations