© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 119090
    Prev
    Next
    INDEX
    Explanations

    though / although

    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_27_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
    కొ
    0.32
    DELAY
    0.30
     기간
    0.30
     ਲੋ
    0.30
     도입
    0.30
     spacers
    0.30
     탄
    0.30
    銠
    0.30
    ᄋ
    0.30
     RETURNS
    0.29
    POSITIVE LOGITS
    или
    0.34
    кину
    0.32
    Though
    0.32
    中医
    0.32
    fotos
    0.31
     perten
    0.31
     though
    0.30
    complete
    0.30
     possède
    0.30
    etor
    0.30
    Activations Density 0.003%

    No Known Activations