© 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. 46854
    Prev
    Next
    INDEX
    Explanations

    message broadcast

    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
    )。
    0.40
    서
    0.40
    ahrt
    0.40
    ᆼ
    0.40
     проходят
    0.39
     З
    0.39
    rai
    0.39
    c
    0.39
     hotter
    0.39
     warmer
    0.38
    POSITIVE LOGITS
    结点
    0.49
    дата
    0.49
    setVisibility
    0.48
    ковым
    0.48
    StillWater
    0.46
     segi
    0.45
     clandest
    0.45
    Idents
    0.45
    StringUtils
    0.45
    🧙
    0.45
    Activations Density 0.000%

    No Known Activations