© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83269
    Prev
    Next
    INDEX
    Explanations

    parentheses or punctuation

    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_29_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
    /
    0.75
    หรือ
    0.66
     aka
    0.64
    或
    0.61
     или
    0.59
     AKA
    0.58
     లేదా
    0.58
     또는
    0.56
     அல்லது
    0.53
     혹은
    0.53
    POSITIVE LOGITS
     ਅਤੇ
    0.44
     καὶ
    0.42
     ແລະ
    0.39
    ítása
    0.38
     եւ
    0.38
     পুস্তক
    0.37
    뇰
    0.37
    ですし
    0.37
    看见
    0.35
     presupp
    0.35
    Activations Density 0.020%

    No Known Activations