© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 1054
    Prev
    Next
    INDEX
    Explanations

    number 76

    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_38_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
     рада
    0.42
    फुल
    0.41
     tố
    0.38
    NumberOf
    0.36
    tagged
    0.36
    ്രാ
    0.36
    เล
    0.35
     ܘ
    0.35
    留
    0.35
     quo
    0.35
    POSITIVE LOGITS
    计时
    0.40
     biên
    0.40
    abic
    0.38
     contemplated
    0.37
    Alice
    0.36
    (:,:,
    0.36
    hect
    0.36
     Lao
    0.35
    ওয়ে
    0.35
    이니
    0.35
    Activations Density 0.003%

    No Known Activations