© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92158
    Prev
    Next
    INDEX
    Explanations

    backporting code and fixes

    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_11_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
    Ｓ
    0.62
     Юлия
    0.57
    ｏ
    0.55
    ඈ
    0.54
    안
    0.54
    ید
    0.53
     jedan
    0.53
    ιού
    0.53
     Sandler
    0.53
    ং
    0.53
    POSITIVE LOGITS
    D
    0.61
    s
    0.57
    M
    0.56
    terre
    0.55
    N
    0.55
    សូម
    0.54
     يصبح
    0.54
     inverse
    0.52
     reversing
    0.49
     récip
    0.49
    Activations Density 0.000%

    No Known Activations