© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7198
    Prev
    Next
    INDEX
    Explanations

    incoming request object

    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_39_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
     particle
    0.40
    стема
    0.40
     Candidate
    0.39
    Notify
    0.38
    िफाई
    0.38
    БК
    0.37
     কণ
    0.37
    忽
    0.37
     formulario
    0.36
     cookbooks
    0.36
    POSITIVE LOGITS
    电话
    0.37
    绮
    0.35
     évol
    0.34
     objectifs
    0.34
    acknowled
    0.34
    aju
    0.33
    ственно
    0.32
    Rack
    0.32
     руко
    0.32
    軽
    0.32
    Activations Density 0.016%

    No Known Activations