© 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. 166194
    Prev
    Next
    INDEX
    Explanations

    QML programming

    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
    ഛ
    0.34
    ంగ
    0.32
     RFID
    0.30
     polycrystalline
    0.30
    ່າງ
    0.30
     Injury
    0.29
     다양
    0.29
    招聘
    0.29
     wounding
    0.29
     разгово
    0.29
    POSITIVE LOGITS
     Plessis
    0.32
     Sriniv
    0.31
    //}
    0.30
     ́
    0.29
    🠀
    0.29
    Zombie
    0.29
    swe
    0.28
     demons
    0.28
    Butler
    0.28
    setzen
    0.28
    Activations Density 0.001%

    No Known Activations