© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89334
    Prev
    Next
    INDEX
    Explanations

    care to admit/count/give/remember/etc

    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_3_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
    ut
    0.74
    ↵
    0.70
    lowing
    0.70
    increased
    0.70
    ाइ
    0.66
    ig
    0.66
    ט
    0.65
    ificación
    0.64
    p
    0.64
    тран
    0.63
    POSITIVE LOGITS
    বে
    0.66
    ল
    0.63
    ва
    0.62
    CAL
    0.61
    ו
    0.59
     và
    0.59
    し
    0.57
    て
    0.57
    将
    0.57
    植
    0.57
    Activations Density 0.001%

    No Known Activations