© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39014
    Prev
    Next
    INDEX
    Explanations

    board separators

    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_11_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
    8
    0.44
    :
    0.43
    7
    0.39
    你
    0.39
    ８
    0.38
    約
    0.38
    （
    0.37
     on
    0.35
    ٨
    0.35
    4
    0.35
    POSITIVE LOGITS
    ajaran
    0.40
     આજ
    0.39
     Humanitarian
    0.39
     Моло
    0.38
     Alguns
    0.36
     Trabalho
    0.35
     Freedom
    0.35
     Слова
    0.35
     Multicultural
    0.35
     فوجی
    0.35
    Activations Density 0.019%

    No Known Activations