© 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. 45058
    Prev
    Next
    INDEX
    Explanations

    text formatting and color codes

    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
     third
    0.41
     hry
    0.38
     readily
    0.38
     ছ
    0.38
     khó
    0.38
     railway
    0.37
     glazed
    0.37
     hideous
    0.37
     Skyscrapers
    0.37
     이는
    0.37
    POSITIVE LOGITS
    Char
    0.44
    월
    0.42
    Message
    0.40
    melody
    0.40
    IS
    0.39
    Balance
    0.39
    launcher
    0.39
    Aile
    0.39
    Soft
    0.38
    Authenticator
    0.38
    Activations Density 0.001%

    No Known Activations