© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54256
    Prev
    Next
    INDEX
    Explanations

    end of documentation

    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_31_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
    പ്പെടുന്നു
    0.40
     передви
    0.40
    ="_
    0.39
     iced
    0.39
    Sometimes
    0.38
     whereas
    0.37
    ánto
    0.36
    有無
    0.36
    責
    0.36
     Sometimes
    0.36
    POSITIVE LOGITS
    🎇
    0.46
    ziehungen
    0.39
    QUE
    0.39
    불
    0.38
    qe
    0.38
    糀
    0.38
     consecut
    0.37
    acije
    0.35
     عدم
    0.35
    QE
    0.35
    Activations Density 0.009%

    No Known Activations