© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18754
    Prev
    Next
    INDEX
    Explanations

    navigating menus: Preferences and 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_15_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
    this
    0.57
    ރ
    0.55
    his
    0.55
    various
    0.51
    ry
    0.51
    Adrian
    0.49
     Adrian
    0.49
    ції
    0.48
    with
    0.48
     seconded
    0.47
    POSITIVE LOGITS
     гли
    0.59
    lycer
    0.56
     Ичиго
    0.54
    蒴
    0.54
    ๔
    0.53
    )=[
    0.53
     EMPC
    0.52
     dissoci
    0.52
     microtubules
    0.51
     Encoding
    0.50
    Activations Density 0.005%

    No Known Activations