© 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. 10258
    Prev
    Next
    INDEX
    Explanations

    8f or redis host

    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
    s
    0.28
    as
    0.28
    溯
    0.25
    旨
    0.25
    为人
    0.24
    into
    0.24
    endente
    0.23
    吸
    0.23
    茄
    0.23
    識別
    0.22
    POSITIVE LOGITS
    ту
    0.32
    एम
    0.32
     که
    0.32
    که
    0.31
     that
    0.31
    ທີ່
    0.31
     rebuilding
    0.31
     PEOPLE
    0.31
    우
    0.31
     capace
    0.30
    Activations Density 0.003%

    No Known Activations