© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17500
    Prev
    Next
    INDEX
    Explanations

    PC

    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_15_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
    ン
    0.58
    ᱨ
    0.57
    ގ
    0.57
    اقة
    0.55
     leyenda
    0.55
    ूप
    0.54
    ्यून
    0.54
     española
    0.54
    ِر
    0.54
    Ⲟ
    0.54
    POSITIVE LOGITS
    both
    0.54
     Klinefelter
    0.51
    oleh
    0.51
    kind
    0.50
    jah
    0.49
    mina
    0.48
    we
    0.48
    ehl
    0.48
    hand
    0.47
     Alabama
    0.47
    Activations Density 0.002%

    No Known Activations