© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144595
    Prev
    Next
    INDEX
    Explanations

    court and Russian words

    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_0_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
    ri
    1.43
    ly
    1.30
    ul
    1.28
    lo
    1.23
    1
    1.22
     I
    1.17
    들이
    1.16
    at
    1.14
    that
    1.13
    ina
    1.12
    POSITIVE LOGITS
    UT
    1.81
    িয়া
    1.52
     azienda
    1.48
     ০
    1.45
    ج
    1.36
    सी
    1.28
    بی
    1.27
    ش
    1.27
    ０
    1.27
    ྥ
    1.27
    Activations Density 0.000%

    No Known Activations