© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223448
    Prev
    Next
    INDEX
    Explanations

    problem

    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_10_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
    o
    0.67
    പം
    0.46
    렜
    0.46
    s
    0.45
    ē
    0.45
    явить
    0.44
    g
    0.43
     specializes
    0.42
    鋃
    0.42
     о
    0.42
    POSITIVE LOGITS
    on
    0.63
    Ми
    0.55
    使用
    0.54
    <h2>
    0.54
    种植
    0.49
    ك
    0.49
    UM
    0.48
    Ма
    0.47
     Cover
    0.47
    Ри
    0.46
    Activations Density 0.028%

    No Known Activations