© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16750
    Prev
    Next
    INDEX
    Explanations

    Some parts

    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_34_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
     nữa
    0.40
    녕하세요
    0.38
     Bullet
    0.36
     /
    0.36
     định
    0.36
     compos
    0.35
     pleadings
    0.35
     આવા
    0.35
    Ꮞ
    0.34
     compone
    0.34
    POSITIVE LOGITS
     turi
    0.46
    은
    0.46
    は
    0.44
     имеет
    0.43
    mtq
    0.42
    atih
    0.42
     have
    0.41
     memiliki
    0.41
     mempunyai
    0.41
     possède
    0.41
    Activations Density 0.112%

    No Known Activations