© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213518
    Prev
    Next
    INDEX
    Explanations

    To

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
    答
    0.51
     answering
    0.50
     answered
    0.46
     जवाब
    0.45
    answer
    0.44
     Đáp
    0.43
     answer
    0.43
     ответить
    0.42
     resposta
    0.42
    ishu
    0.41
    POSITIVE LOGITS
     Hicks
    0.44
     иң
    0.43
    Reading
    0.41
     읽
    0.41
    閱讀
    0.41
     Rick
    0.40
    Rick
    0.40
     Allies
    0.39
     Reading
    0.39
     reading
    0.39
    Activations Density 0.001%

    No Known Activations