© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36417
    Prev
    Next
    INDEX
    Explanations

    SQL index and key definitions

    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
     facies
    0.63
    <0x80>
    0.57
     ambulatory
    0.56
     younger
    0.55
    най
    0.55
     siku
    0.55
     guardian
    0.55
     fluorine
    0.55
     testigo
    0.52
     fascia
    0.52
    POSITIVE LOGITS
    ج
    0.50
    ència
    0.49
    ၇
    0.48
    gi
    0.47
     “‘
    0.47
    ائدة
    0.46
    gain
    0.46
     Rarely
    0.46
    𝑔
    0.46
     直接
    0.46
    Activations Density 0.010%

    No Known Activations