© 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. 194204
    Prev
    Next
    INDEX
    Explanations

    browser and amendment

    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
    {
    0.61
    G
    0.59
    I
    0.58
    O
    0.54
    GN
    0.53
    Ｄ
    0.52
     $
    0.52
    विश्
    0.50
     W
    0.49
    View
    0.49
    POSITIVE LOGITS
    omeness
    0.55
    alı
    0.54
     پل
    0.54
     venting
    0.52
    ophytic
    0.52
     وهكذا
    0.52
     omitting
    0.50
     között
    0.50
    …).
    0.48
     insults
    0.47
    Activations Density 0.001%

    No Known Activations