© 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
    2. Gemma-3-27B-IT
    3. 37-GEMMASCOPE-2-TRANSCODER-262K
    4. 124503
    Prev
    Next
    INDEX
    Explanations

    type annotations

    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_37_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
    তল
    0.43
     मार्केट
    0.39
    Oliv
    0.37
     despised
    0.37
    🍒
    0.36
    জিওথেরাপি
    0.36
    迪
    0.36
    反應
    0.35
     やす
    0.35
     товара
    0.35
    POSITIVE LOGITS
     type
    0.62
    type
    0.57
     typu
    0.57
     نوع
    0.55
    نوع
    0.55
     tipo
    0.54
    型
    0.49
     типа
    0.48
    OfType
    0.48
    型的
    0.47
    Activations Density 0.210%

    No Known Activations