© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84255
    Prev
    Next
    INDEX
    Explanations

    transparency settings

    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_0_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
     an
    1.45
     on
    1.28
     It
    1.27
    ки
    1.27
    出
    1.27
    е
    1.25
     في
    1.24
    行
    1.24
    し
    1.20
    是
    1.20
    POSITIVE LOGITS
    ພວກເຮ
    1.45
    ESI
    1.45
    quela
    1.42
    О
    1.41
    5
    1.41
    ką
    1.40
    kiej
    1.40
    ຜະລິດຕະພັນ
    1.40
    ພວກເຮົາ
    1.38
     convexes
    1.36
    Activations Density 0.000%

    No Known Activations