© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196736
    Prev
    Next
    INDEX
    Explanations

    WMethod used: 1

    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_46_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
     Expect
    0.43
     ভগবান
    0.36
     एक्सपेक्ट
    0.36
     опера
    0.36
     অধ্যাপক
    0.36
    ඕ
    0.35
     dú
    0.35
    కి
    0.35
    Expect
    0.35
     தந்த
    0.35
    POSITIVE LOGITS
     Jr
    0.43
    issance
    0.38
     무게
    0.38
     Jac
    0.37
     g
    0.36
     Wy
    0.36
    垕
    0.35
    臾
    0.35
     py
    0.35
     Horne
    0.35
    Activations Density 0.001%

    No Known Activations