© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11501
    Prev
    Next
    INDEX
    Explanations

    chan, forum, boards

    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_13_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
    州
    0.63
    远
    0.55
    頴
    0.54
    杵
    0.53
    Ethnic
    0.52
     syrups
    0.52
     Länder
    0.51
    Koordin
    0.50
    വശ
    0.50
    স্থ
    0.49
    POSITIVE LOGITS
    ie
    0.63
    _{
    0.61
    ieva
    0.61
     forums
    0.61
    становка
    0.60
    message
    0.56
    bbs
    0.55
     culpa
    0.55
    ord
    0.54
    forum
    0.54
    Activations Density 0.037%

    No Known Activations