© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144870
    Prev
    Next
    INDEX
    Explanations

    contextual meaning and understanding

    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_0_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
    I
    1.75
    an
    1.45
    ł
    1.37
    های
    1.36
    ות
    1.35
    *
    1.27
    ג
    1.27
    ي
    1.27
    A
    1.26
    들이
    1.20
    POSITIVE LOGITS
     are
    1.82
    ní
    1.70
    的
    1.63
    用
    1.45
    níci
    1.37
    níka
    1.34
     to
    1.27
     have
    1.26
    é
    1.26
     utilise
    1.20
    Activations Density 0.001%

    No Known Activations