© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92803
    Prev
    Next
    INDEX
    Explanations

    in a sense

    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_11_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
    C
    0.64
    F
    0.63
    Т
    0.57
    P
    0.57
    K
    0.55
    Q
    0.55
    G
    0.54
    Д
    0.54
    JSON
    0.53
    К
    0.52
    POSITIVE LOGITS
     Düsseldorf
    0.52
    啇
    0.52
    anço
    0.50
     Después
    0.49
    ρίας
    0.49
     एग्जाम
    0.48
     MERCHANT
    0.48
     vårt
    0.48
     isomerization
    0.48
    ra
    0.48
    Activations Density 0.001%

    No Known Activations