© 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. 137730
    Prev
    Next
    INDEX
    Explanations

    programming concepts

    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
    ീസ്
    0.47
    雑誌
    0.44
    <0xF1>
    0.42
    იმე
    0.41
    צוני
    0.41
     maaaring
    0.41
    benius
    0.40
    дание
    0.40
     כן
    0.40
    貿
    0.39
    POSITIVE LOGITS
     G
    0.40
     Script
    0.40
     Cli
    0.39
    Cl
    0.35
    घो
    0.35
     script
    0.35
    CL
    0.34
    Script
    0.34
     CL
    0.34
     irre
    0.34
    Activations Density 0.000%

    No Known Activations