© 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. 162945
    Prev
    Next
    INDEX
    Explanations

    file extensions and URLs

    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
    嘞
    0.42
     obsol
    0.41
     жить
    0.37
     Dates
    0.36
    軻
    0.35
    Date
    0.34
    moor
    0.34
     vivir
    0.33
     allt
    0.33
     effort
    0.32
    POSITIVE LOGITS
     blijkt
    0.37
     Özellikle
    0.37
    войства
    0.37
     ơi
    0.35
     bust
    0.35
    怡
    0.35
     ماش
    0.35
     Kabir
    0.35
     คลิป
    0.35
    Apparently
    0.34
    Activations Density 0.003%

    No Known Activations