© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194688
    Prev
    Next
    INDEX
    Explanations

    maximal/maximum

    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_15_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
    和
    0.55
     Tattha
    0.54
     Rockford
    0.53
    ப்புற
    0.52
    한국
    0.50
    WordPress
    0.50
     становништво
    0.49
     आसपास
    0.49
     Lakewood
    0.49
    지와
    0.49
    POSITIVE LOGITS
    c
    0.80
     rilev
    0.51
    wab
    0.50
     “(
    0.50
    isi
    0.50
     IN
    0.49
     TEST
    0.49
     unaccount
    0.48
    ма
    0.48
     not
    0.47
    Activations Density 0.001%

    No Known Activations