© 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. 23895
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     tired
    1.09
    tired
    0.95
     Tired
    0.90
     tiredness
    0.82
     fatigue
    0.81
     fatigued
    0.79
    疲
    0.72
     Fatigue
    0.72
     hungry
    0.69
     exhausted
    0.64
    POSITIVE LOGITS
    ð
    0.61
    ði
    0.60
    ða
    0.60
    Þ
    0.59
     ð
    0.53
    að
    0.52
     að
    0.50
     ¼
    0.49
    ½
    0.49
    þ
    0.48
    Activations Density 0.014%

    No Known Activations