© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228469
    Prev
    Next
    INDEX
    Explanations

    countries

    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_6_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
    an
    1.27
    9
    1.14
    es
    1.11
    ان
    1.07
    a
    0.95
    ar
    0.93
    ’
    0.90
    it
    0.86
    6
    0.82
    ra
    0.81
    POSITIVE LOGITS
    ز
    0.91
    ک
    0.91
    UM
    0.85
     be
    0.84
    مة
    0.81
     Guzmán
    0.80
    ﺓ
    0.79
    ON
    0.78
    ди
    0.77
    IS
    0.76
    Activations Density 0.003%

    No Known Activations