© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125279
    Prev
    Next
    INDEX
    Explanations

    Kankakee, Konkani, KEK

    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_3_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
    ing
    0.74
    ة
    0.65
    ुरा
    0.64
    ны
    0.63
    ือง
    0.63
    েশের
    0.58
    งาน
    0.58
    ”、“
    0.55
    یر
    0.54
     Capac
    0.53
    POSITIVE LOGITS
    t
    0.82
    {
    0.77
    ों
    0.70
     उदाहरण
    0.66
     ruộng
    0.65
    ﺭ
    0.65
    s
    0.65
    ের
    0.64
    ált
    0.63
     arranging
    0.61
    Activations Density 0.000%

    No Known Activations