© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221939
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    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
     )))
    0.59
    na
    0.58
    ्युअर
    0.57
    ۶
    0.57
    Carrito
    0.55
     CCCC
    0.55
     grenades
    0.55
    ಿಂತ
    0.54
     иң
    0.54
     Cnemidophorus
    0.54
    POSITIVE LOGITS
    s
    0.89
    ال
    0.65
    a
    0.60
    一
    0.57
    ంగా
    0.56
    :
    0.56
    ed
    0.56
    مل
    0.54
    ه
    0.54
    长期
    0.53
    Activations Density 0.003%

    No Known Activations