© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89179
    Prev
    Next
    INDEX
    Explanations

    Cisco Systems, Spice Girls, protein

    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_3_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
    2
    0.78
    4
    0.73
    1
    0.72
     (
    0.70
    3
    0.63
     to
    0.62
    to
    0.58
    0
    0.57
    каза
    0.56
    <=
    0.56
    POSITIVE LOGITS
    is
    0.86
     découvre
    0.75
    ის
    0.70
    el
    0.70
     conseille
    0.68
    O
    0.68
     couronne
    0.67
    emiz
    0.66
    ها
    0.65
    équipe
    0.65
    Activations Density 0.000%

    No Known Activations