© 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. 144714
    Prev
    Next
    INDEX
    Explanations

    slippery rocks and skin

    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
    는
    2.31
    是
    1.94
    は
    1.88
    其他
    1.78
    ب
    1.69
    د
    1.65
    ق
    1.42
    その
    1.39
    ج
    1.38
    ف
    1.30
    POSITIVE LOGITS
    la
    1.52
    ką
    1.46
     enfant
    1.40
    ور
    1.30
    sType
    1.27
    sa
    1.27
    )
    1.25
    ет
    1.23
    ري
    1.23
    lama
    1.21
    Activations Density 0.000%

    No Known Activations