© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11761
    Prev
    Next
    INDEX
    Explanations

    numbers or specific 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_13_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
    insect
    0.47
    better
    0.46
     لیکن
    0.46
    ﹕
    0.46
     కొన్ని
    0.45
    es
    0.45
    arkan
    0.45
    <0xA0>
    0.44
     වඩා
    0.44
    ha
    0.44
    POSITIVE LOGITS
     pr
    0.45
    に入
    0.45
     *
    0.44
     הא
    0.43
     cop
    0.40
     recept
    0.40
     [
    0.38
     physical
    0.38
     preparation
    0.38
     referred
    0.38
    Activations Density 0.016%

    No Known Activations