© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83161
    Prev
    Next
    INDEX
    Explanations

    federal court system

    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_29_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
     উপমহাদেশ
    0.37
    ஜி
    0.36
     Índ
    0.35
     compétence
    0.35
    posure
    0.35
     impatience
    0.34
     €,
    0.34
     positivas
    0.34
     eğ
    0.34
    posición
    0.34
    POSITIVE LOGITS
    ﾜ
    0.40
    wrote
    0.38
     herringbone
    0.37
    filer
    0.37
     venture
    0.36
    ಟ್ಟಿ
    0.36
    oughed
    0.36
    대의
    0.36
    漑
    0.36
    ocolate
    0.36
    Activations Density 0.001%

    No Known Activations