© 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. 249894
    Prev
    Next
    INDEX
    Explanations

    focus; emphasis

    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
     Ê
    1.14
    Ê
    0.96
     ê
    0.83
     Â
    0.77
     â
    0.76
     Ô
    0.73
    ÂN
    0.70
    ân
    0.70
     û
    0.70
    ê
    0.67
    POSITIVE LOGITS
     emphasis
    0.67
     focus
    0.65
     Emphasis
    0.63
    Emphasis
    0.60
    focus
    0.57
     Focus
    0.57
    emphasis
    0.57
    Focus
    0.55
    ó
    0.54
    FOCUS
    0.50
    Activations Density 0.004%

    No Known Activations