© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14499
    Prev
    Next
    INDEX
    Explanations

    intensifier (very, muy)

    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_13_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
    在
    0.52
     comest
    0.52
     obser
    0.51
    เมื่อ
    0.50
     choline
    0.44
     neut
    0.44
     menu
    0.43
    L
    0.43
     doct
    0.43
     pries
    0.42
    POSITIVE LOGITS
     Kecamatan
    0.41
    ten
    0.40
    hearing
    0.39
     Municipality
    0.39
    haven
    0.39
    mson
    0.39
    protective
    0.39
    fuzzy
    0.39
    iyasi
    0.39
    populated
    0.39
    Activations Density 0.129%

    No Known Activations