© 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. 6979
    Prev
    Next
    INDEX
    Explanations

    `.py` file extension

    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
    㖵
    0.32
     écrit
    0.30
     geven
    0.30
     written
    0.30
     دادن
    0.29
     myWeb
    0.29
     FontSize
    0.29
     julho
    0.29
     девушки
    0.29
     देता
    0.29
    POSITIVE LOGITS
    Список
    0.32
    ¡
    0.31
     ¡
    0.30
    pack
    0.29
    cap
    0.29
    scapes
    0.29
     Bloody
    0.29
     clas
    0.29
    زا
    0.28
     શ્રે
    0.28
    Activations Density 0.017%

    No Known Activations