© 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. 4051
    Prev
    Next
    INDEX
    Explanations

    specific punctuation followed by a declarative word

    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
     hồi
    0.40
     Could
    0.38
    廛
    0.38
     could
    0.37
    Could
    0.36
     Chalmers
    0.36
     обна
    0.36
     回
    0.35
    ICS
    0.35
    ♥️
    0.34
    POSITIVE LOGITS
     mark
    1.15
    mark
    0.99
     marks
    0.88
    マーク
    0.87
     Mark
    0.85
    marks
    0.84
    Mark
    0.81
     MARK
    0.78
     マーク
    0.77
     marking
    0.77
    Activations Density 0.033%

    No Known Activations