© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 90226
    Prev
    Next
    INDEX
    Explanations

    MCG or neurochemistry

    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_23_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    anta
    0.42
    agements
    0.42
    estructive
    0.42
    菪
    0.40
    cycle
    0.40
    structure
    0.38
    zele
    0.38
    cycles
    0.37
    缠
    0.37
    ologico
    0.37
    POSITIVE LOGITS
    ハ
    0.44
    ウィ
    0.42
     multiple
    0.40
    ナイ
    0.38
    別途
    0.37
     مار
    0.37
    日
    0.37
     ज़र
    0.37
     ब्ल
    0.37
    CSV
    0.36
    Activations Density 0.000%

    No Known Activations