© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169763
    Prev
    Next
    INDEX
    Explanations

    say "clock"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    accounts
    0.39
    Times
    0.39
     cl
    0.38
    resser
    0.38
    Resolution
    0.38
    Hosting
    0.38
    
    0.38
     চুম্বন
    0.38
    Cl
    0.37
    times
    0.37
    POSITIVE LOGITS
     wall
    0.67
     ch
    0.52
    wall
    0.51
     Wall
    0.49
     दीवार
    0.46
    WALL
    0.46
     WALL
    0.45
    壁
    0.43
     벽
    0.43
     choker
    0.42
    Activations Density 0.002%

    No Known Activations