© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48765
    Prev
    Next
    INDEX
    Explanations

    trick, future, mist, upper, typical

    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_10_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
    frozen
    0.56
     húmed
    0.54
    ños
    0.54
     dejó
    0.51
    r
    0.51
     ángulo
    0.50
    ízo
    0.49
     tierra
    0.49
    ról
    0.49
     alegre
    0.49
    POSITIVE LOGITS
    नेक
    0.46
    相
    0.44
    ᆸ
    0.43
    有可能
    0.41
    ുമെന്ന്
    0.41
    年
    0.40
    आय
    0.40
    ้วน
    0.39
     mammalian
    0.39
    開業
    0.39
    Activations Density 0.000%

    No Known Activations