© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17770
    Prev
    Next
    INDEX
    Explanations

    end of html body

    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_40_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
    DEFINE
    0.39
     ወ
    0.39
     dto
    0.39
     αγο
    0.36
    ಂಧ
    0.36
    дика
    0.36
     notifying
    0.35
    ಿದ್ದಾನೆ
    0.35
    சியம்
    0.35
     మధ్య
    0.35
    POSITIVE LOGITS
    ↕
    0.43
     높
    0.36
     Fen
    0.35
    盆
    0.35
    高さ
    0.35
     hauteur
    0.35
    코드
    0.34
     Height
    0.34
    寄り
    0.34
     Tail
    0.33
    Activations Density 0.002%

    No Known Activations