© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49581
    Prev
    Next
    INDEX
    Explanations

    cycle

    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_55_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
     back
    0.79
    回
    0.74
     ret
    0.68
     Back
    0.67
     回
    0.61
     BACK
    0.61
    Back
    0.59
    back
    0.56
     Ret
    0.54
    BACK
    0.54
    POSITIVE LOGITS
    cycle
    0.39
    Cycle
    0.39
    ніх
    0.38
    져
    0.37
    underline
    0.37
    뢨
    0.37
    cycles
    0.37
    counted
    0.36
    circled
    0.36
    fly
    0.35
    Activations Density 0.010%

    No Known Activations