© 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. 37127
    Prev
    Next
    INDEX
    Explanations

    patting yourself or himself

    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
     {
    0.61
     registr
    0.61
     confirm
    0.60
     Waalaikumsalam
    0.59
     glancing
    0.58
     turban
    0.58
     WTA
    0.57
     WAIT
    0.56
     pronunci
    0.55
     spust
    0.54
    POSITIVE LOGITS
    wells
    0.70
    ų
    0.66
    ponds
    0.65
    ind
    0.64
    water
    0.64
    citizens
    0.63
    uestos
    0.61
    ൩
    0.61
    ون
    0.61
    acons
    0.60
    Activations Density 0.005%

    No Known Activations