© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9670
    Prev
    Next
    INDEX
    Explanations

    birds and animals

    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
     military
    0.58
     Military
    0.54
     militaire
    0.49
    军
    0.49
     Quân
    0.48
     NATO
    0.47
    Military
    0.46
    Army
    0.46
    军事
    0.46
    ش
    0.45
    POSITIVE LOGITS
    テンツ
    0.48
     integrate
    0.47
     テーマ
    0.46
     イ
    0.46
    hattisgarh
    0.46
    巔
    0.46
    ತ್ಮ
    0.46
     브랜드
    0.45
     영역
    0.44
     指定
    0.44
    Activations Density 0.009%

    No Known Activations