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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201325
    Prev
    Next
    INDEX
    Explanations

    underdeveloped and development

    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_12_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
     Microscope
    0.61
    <0x83>
    0.58
     Galileo
    0.56
     Labrador
    0.55
     Nature
    0.55
     rinsing
    0.54
     Antarctic
    0.54
     खरीदने
    0.54
     Publ
    0.54
     rued
    0.53
    POSITIVE LOGITS
    plet
    0.55
    login
    0.52
    ק
    0.52
    ”)
    0.50
    find
    0.49
    st
    0.48
     digits
    0.47
    ereg
    0.46
     qar
    0.46
    ID
    0.46
    Activations Density 0.012%

    No Known Activations