© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 244293
    Prev
    Next
    INDEX
    Explanations

    Motrin

    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_40_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
     శ్రీ
    0.44
     Ashley
    0.42
     sdf
    0.42
     SBA
    0.42
     annak
    0.42
     શ્રી
    0.42
    狼
    0.41
     আশ্র
    0.40
     ub
    0.39
     yy
    0.39
    POSITIVE LOGITS
     rô
    0.38
    tec
    0.37
    Ré
    0.37
    voicing
    0.36
     flipping
    0.35
    Glor
    0.35
    fitting
    0.35
     ca
    0.34
     Sprague
    0.34
    翻
    0.34
    Activations Density 0.003%

    No Known Activations