© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 91838
    Prev
    Next
    INDEX
    Explanations

    everything you

    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
     ,
    0.42
    test
    0.37
     quiz
    0.34
     for
    0.34
    no
    0.34
     graffiti
    0.33
    g
    0.33
    new
    0.32
    find
    0.32
     ,"
    0.32
    POSITIVE LOGITS
     أي
    0.36
    ប្រតិ
    0.35
     كيف
    0.34
    یان
    0.34
     বিষয়
    0.34
    𝑭
    0.34
    弹性
    0.33
    ົວ
    0.32
    芢
    0.31
    ../../
    0.30
    Activations Density 0.026%

    No Known Activations