© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149539
    Prev
    Next
    INDEX
    Explanations

    morning

    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_59_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
    朝
    1.60
     朝
    1.02
     dawn
    0.72
    Dawn
    0.71
    dawn
    0.68
     Dawn
    0.66
    朝着
    0.59
    صبح
    0.57
     sunrise
    0.51
     morning
    0.50
    POSITIVE LOGITS
    早
    1.91
     early
    1.90
    early
    1.75
     Early
    1.66
    Early
    1.66
     EARLY
    1.56
     早
    1.52
     früh
    1.51
     الص
    1.38
     아
    1.29
    Activations Density 0.000%

    No Known Activations