© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34168
    Prev
    Next
    INDEX
    Explanations

    words following 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_31_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
    чески
    0.04
    咔
    0.04
    eken
    0.04
     tind
    0.04
     crim
    0.04
    Easing
    0.04
     useRef
    0.04
    étaires
    0.04
    ละคร
    0.04
    ‵
    0.04
    POSITIVE LOGITS
     harn
    0.04
    グラス
    0.04
     హైదర్
    0.04
     Dre
    0.04
     ugly
    0.04
    မျှ
    0.04
     hopeless
    0.04
     zau
    0.04
     astonishment
    0.04
     dre
    0.03
    Activations Density 0.001%

    No Known Activations