© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195607
    Prev
    Next
    INDEX
    Explanations

    leaf spot or litter

    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_4_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
    ת
    1.30
    ة
    1.02
    ২
    0.96
    ер
    0.93
    ра
    0.92
    א
    0.90
    ц
    0.85
    خ
    0.85
    ৩
    0.85
    وس
    0.84
    POSITIVE LOGITS
    1.26
     for
    1.16
    o
    1.06
    .
    1.05
    y
    1.05
    a
    1.03
    h
    0.99
     a
    0.83
    m
    0.83
    arı
    0.80
    Activations Density 0.003%

    No Known Activations