© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 204158
    Prev
    Next
    INDEX
    Explanations

    lot

    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
    なくても
    0.45
    adura
    0.41
    细
    0.40
     inflection
    0.39
    ']==
    0.38
    effort
    0.38
     थोड़ा
    0.38
     ग्रे
    0.37
    IDEA
    0.37
    insen
    0.37
    POSITIVE LOGITS
     মর্যা
    0.42
     بنیاد
    0.40
    Awesome
    0.40
     দুর্দান্ত
    0.39
    льній
    0.39
    すべき
    0.38
     %=
    0.38
     grandes
    0.38
     большие
    0.38
     Curling
    0.38
    Activations Density 0.005%

    No Known Activations