© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177129
    Prev
    Next
    INDEX
    Explanations

    Sonic Pi

    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_50_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
     அரு
    0.43
    re
    0.41
    ako
    0.38
    });
    0.37
    keys
    0.37
    consulté
    0.37
    act
    0.37
    ph
    0.37
    cer
    0.37
     ছি
    0.37
    POSITIVE LOGITS
     Wrangler
    0.43
    کان
    0.42
     кан
    0.39
     euclidean
    0.38
     Husk
    0.38
     చేశ
    0.38
    逭
    0.38
     کان
    0.38
     Khánh
    0.38
    ություններ
    0.38
    Activations Density 0.001%

    No Known Activations