© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5539
    Prev
    Next
    INDEX
    Explanations

    check if command -v

    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
    ฐ
    0.33
    িকার
    0.31
    mission
    0.31
    rought
    0.31
    êm
    0.30
    ماه
    0.30
     tàu
    0.30
    érus
    0.30
     Kaz
    0.29
     Vessels
    0.29
    POSITIVE LOGITS
    ವಲ್ಲ
    0.39
     whip
    0.37
     seventy
    0.35
    簾
    0.34
     Whip
    0.34
     Seventy
    0.33
     whipping
    0.33
    ７
    0.33
     மோ
    0.32
     மது
    0.32
    Activations Density 0.001%

    No Known Activations