© 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. 223288
    Prev
    Next
    INDEX
    Explanations

    genes and genetics

    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
    as
    0.18
    _
    0.18
    ן
    0.16
    ו
    0.15
    ান
    0.15
    т
    0.15
    Loren
    0.14
    ת
    0.14
    та
    0.14
    ם
    0.14
    POSITIVE LOGITS
     বিশ্ববিদ্যালয়ের
    0.14
    िप्ट
    0.12
     և
    0.12
     नये
    0.11
    inition
    0.11
     메서
    0.11
    inationals
    0.11
     फ़
    0.11
     नारे
    0.11
     الجام
    0.11
    Activations Density 0.016%

    No Known Activations