© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 146175
    Prev
    Next
    INDEX
    Explanations

    secession crisis

    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_0_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
    س
    1.60
    ts
    1.54
    स
    1.43
    the
    1.38
     (
    1.33
    ta
    1.25
    า
    1.25
    тся
    1.24
    าย
    1.23
    6
    1.23
    POSITIVE LOGITS
    اي
    1.53
    elijke
    1.45
     التيار
    1.43
     كيف
    1.39
     ganador
    1.39
     französ
    1.37
    ků
    1.34
     wichtig
    1.34
     acceso
    1.30
    مي
    1.30
    Activations Density 0.000%

    No Known Activations