© 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. 9871
    Prev
    Next
    INDEX
    Explanations

    striking beauty or appearance

    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
     toned
    0.40
    toned
    0.39
    Version
    0.38
     شعر
    0.38
    getVersion
    0.37
    ########
    0.37
    ಪು
    0.37
    살
    0.37
     subpo
    0.36
     colours
    0.36
    POSITIVE LOGITS
     Quality
    0.50
     Type
    0.49
     kualitas
    0.49
     Qualität
    0.48
     qualidade
    0.47
     calidad
    0.46
     quality
    0.46
    质量
    0.46
    Quality
    0.45
    quality
    0.45
    Activations Density 0.017%

    No Known Activations