© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52972
    Prev
    Next
    INDEX
    Explanations

    minutes or seconds

    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_30_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
    単
    0.29
     groups
    0.28
    Single
    0.28
     பற்றி
    0.28
    Cell
    0.27
     Dok
    0.27
    менти
    0.27
    Groups
    0.27
    单个
    0.27
    groups
    0.26
    POSITIVE LOGITS
     cataract
    0.34
     نب
    0.29
     ट्रेलर
    0.29
     fisk
    0.28
    ͅ
    0.28
     갈
    0.28
     vsize
    0.28
     potrav
    0.28
     remarquable
    0.27
     dilwale
    0.27
    Activations Density 0.012%

    No Known Activations