© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142185
    Prev
    Next
    INDEX
    Explanations

    san francisco and specialties

    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_0_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
    า
    2.03
    い
    1.73
    ة
    1.73
    ı
    1.70
    ী
    1.66
    ও
    1.56
    ס
    1.52
    ла
    1.46
    ี
    1.46
    ו
    1.44
    POSITIVE LOGITS
     A
    1.85
     I
    1.77
     K
    1.55
     S
    1.52
     T
    1.50
    ，
    1.47
     P
    1.45
     W
    1.45
     H
    1.44
     E
    1.44
    Activations Density 0.000%

    No Known Activations