© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79953
    Prev
    Next
    INDEX
    Explanations

    trains and waiting

    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_31_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
     broth
    0.39
    AHN
    0.39
    所
    0.39
     anchorage
    0.38
    tfine
    0.37
     collaborating
    0.37
    qdm
    0.36
     tending
    0.36
     Collabor
    0.36
    डॉ
    0.36
    POSITIVE LOGITS
     сложные
    0.41
     Reaper
    0.41
    SCHEDULE
    0.37
     упомина
    0.37
    ᅠ
    0.36
     publicités
    0.35
    ကြား
    0.35
    鈴
    0.35
    oyens
    0.34
    schedule
    0.34
    Activations Density 0.002%

    No Known Activations