© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130328
    Prev
    Next
    INDEX
    Explanations

    life and learning

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ลำ
    0.66
     원
    0.50
    lname
    0.48
     lname
    0.46
    원
    0.44
    Wayne
    0.43
     laminate
    0.43
     Wayne
    0.42
    ต้น
    0.42
    tact
    0.42
    POSITIVE LOGITS
    เซอร์
    0.42
     бан
    0.42
     फिज
    0.42
     chy
    0.41
     клуб
    0.41
    菲律
    0.40
    츠
    0.40
     بان
    0.40
     ফিল
    0.40
     ሙ
    0.39
    Activations Density 0.014%

    No Known Activations