© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 67782
    Prev
    Next
    INDEX
    Explanations

    complex tasks

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     principale
    0.43
     рабочей
    0.43
     principal
    0.42
     specification
    0.40
    특
    0.40
    principal
    0.39
    GUI
    0.39
     principais
    0.39
    problems
    0.39
     Specification
    0.38
    POSITIVE LOGITS
    setAutoDraw
    0.37
    ⟺
    0.36
     Noether
    0.36
    νει
    0.36
    ϴ
    0.36
     tâches
    0.35
    צע
    0.35
    痤
    0.35
    MathML
    0.35
     時計
    0.35
    Activations Density 0.016%

    No Known Activations