© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16076
    Prev
    Next
    INDEX
    Explanations

    mark making marking marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    eş
    0.36
    هي
    0.35
    ported
    0.33
     هي
    0.33
    廛
    0.33
     attributable
    0.32
    чы
    0.31
     Benn
    0.31
     Maladies
    0.31
    銓
    0.31
    POSITIVE LOGITS
     mark
    2.58
    mark
    2.27
     marks
    2.23
    Mark
    1.98
     Mark
    1.97
    marks
    1.95
     marking
    1.88
     MARK
    1.87
    マーク
    1.87
    Marks
    1.80
    Activations Density 0.042%

    No Known Activations