© 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
    2. Gemma-3-27B-IT
    3. 14-GEMMASCOPE-2-TRANSCODER-262K
    4. 99145
    Prev
    Next
    INDEX
    Explanations

    count or equal

    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_14_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
    Та
    0.20
    з
    0.17
    ز
    0.17
    І
    0.17
    س
    0.17
    Р
    0.16
    ပ်
    0.16
    ”
    0.16
    网站
    0.16
    ர்
    0.16
    POSITIVE LOGITS
    LOTRE
    0.19
    rett
    0.18
     teorías
    0.18
     కనిప
    0.17
     Lonely
    0.17
    ASDW
    0.17
    iaj
    0.17
     मातरम
    0.17
     comprendere
    0.17
     theories
    0.16
    Activations Density 0.001%

    No Known Activations