© 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-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3377
    Prev
    Next
    INDEX
    Explanations

    zero followed by punctuation or parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    ции
    1.03
    ׁ
    0.95
    ریت
    0.89
    orean
    0.88
    kreis
    0.86
    বহুল
    0.86
    كة
    0.86
    вшейся
    0.86
    ure
    0.85
    た
    0.84
    POSITIVE LOGITS
     önce
    0.98
    xff
    0.97
     adet
    0.93
    ద్య
    0.87
     градусов
    0.84
    ̸
    0.84
     denominators
    0.82
     inund
    0.82
     ocur
    0.81
    fps
    0.80
    Activations Density 0.175%

    No Known Activations