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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57906
    Prev
    Next
    INDEX
    Explanations

    step forward

    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_11_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
    모
    0.14
    Specification
    0.14
    रुण
    0.13
     метро
    0.13
    진다
    0.13
     বিটিআই
    0.13
    сно
    0.13
    며
    0.13
    ээ
    0.13
     KISS
    0.13
    POSITIVE LOGITS
    (
    0.16
     ά
    0.16
    ie
    0.15
     राजद
    0.15
    微软雅黑
    0.15
     e
    0.14
    ord
    0.14
    ья
    0.14
     Mond
    0.14
    ردن
    0.14
    Activations Density 0.002%

    No Known Activations