© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246081
    Prev
    Next
    INDEX
    Explanations

    react hooks and vue-router

    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_40_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
     circle
    0.45
     ambiance
    0.40
     Circle
    0.40
    ფილი
    0.39
     (@
    0.38
     ambience
    0.38
     Pro
    0.37
     юк
    0.37
     pro
    0.36
     circles
    0.36
    POSITIVE LOGITS
     കൊണ്ട്
    0.42
     estrut
    0.38
    carbons
    0.37
    Segundo
    0.37
     കൊണ്ട
    0.37
    Visitors
    0.37
    theory
    0.36
    SLC
    0.36
    ⚫
    0.36
     strutt
    0.35
    Activations Density 0.000%

    No Known Activations