© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84279
    Prev
    Next
    INDEX
    Explanations

    students are taught or mentored

    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_23_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
     재
    0.33
    Arabic
    0.31
     गर
    0.30
     সন
    0.29
    Parents
    0.29
     <
    0.28
    廂
    0.28
    Та
    0.28
    Ба
    0.28
    聖
    0.28
    POSITIVE LOGITS
    risch
    0.36
    rategy
    0.35
     idle
    0.32
    urnya
    0.31
    helves
    0.30
    ccc
    0.30
    amless
    0.30
     vutt
    0.29
     न्यून
    0.29
     sebagai
    0.29
    Activations Density 0.002%

    No Known Activations