© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216451
    Prev
    Next
    INDEX
    Explanations

    Goa, India, Portuguese, Gujarat

    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_31_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
     util
    0.37
     Mitar
    0.36
    μπ
    0.36
    贻
    0.36
     pur
    0.35
     Pur
    0.35
    umiem
    0.35
     pung
    0.35
    echolog
    0.34
     semiconductor
    0.34
    POSITIVE LOGITS
     सिन्हा
    0.39
    otherapy
    0.37
     ممال
    0.37
    鄯
    0.34
    reichen
    0.34
     خواہ
    0.33
     собе
    0.33
    默
    0.33
     Syrup
    0.33
    innitus
    0.32
    Activations Density 0.001%

    No Known Activations