© 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. 37734
    Prev
    Next
    INDEX
    Explanations

    public attention and discussion

    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
     Nikki
    0.40
     संरक्षित
    0.38
    +\
    0.38
     pigments
    0.38
    ké
    0.37
     Landscape
    0.37
     wasn
    0.37
    ON
    0.36
     अकबर
    0.36
    ations
    0.36
    POSITIVE LOGITS
    ة
    0.69
    h
    0.52
    v
    0.52
    い
    0.48
    ing
    0.47
    n
    0.47
    ט
    0.44
    o
    0.43
    트
    0.43
    ა
    0.43
    Activations Density 0.155%

    No Known Activations