© 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. 91190
    Prev
    Next
    INDEX
    Explanations

    embarks on

    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
    _
    0.81
     Η
    0.60
     Leur
    0.57
    elerine
    0.56
     Tew
    0.56
    EMAIL
    0.55
     செய்தனர்
    0.55
    ('
    0.54
    改为
    0.54
     ఏద
    0.54
    POSITIVE LOGITS
     j
    0.68
    к
    0.68
     z
    0.63
    ج
    0.59
    ジ
    0.58
     ju
    0.56
    am
    0.55
     tức
    0.55
    soci
    0.55
    ி
    0.55
    Activations Density 0.001%

    No Known Activations