© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 86143
    Prev
    Next
    INDEX
    Explanations

    associated with "Library" or "Old"

    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_18_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
     เขา
    0.55
     剤
    0.52
     금융
    0.49
     माझी
    0.48
    เขา
    0.47
     Cholesterol
    0.46
    餑
    0.46
     खोसला
    0.46
    唦
    0.46
     कैफ
    0.45
    POSITIVE LOGITS
     desmont
    0.54
     complacency
    0.51
     como
    0.51
     kasarigan
    0.50
    eacute
    0.49
    em
    0.49
     conocimiento
    0.49
     imposes
    0.48
     subjet
    0.48
     concaten
    0.47
    Activations Density 0.000%

    No Known Activations