© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208637
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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_25_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
    ファッション
    0.42
    ントリー
    0.42
    зка
    0.41
     rendent
    0.41
     देतात
    0.40
    ))%>%
    0.39
    ⚉
    0.39
     dauer
    0.39
     fazem
    0.38
    題目
    0.38
    POSITIVE LOGITS
     King
    0.40
     Museum
    0.39
     Black
    0.39
     Adu
    0.36
     Fuller
    0.35
    蝰
    0.35
     Club
    0.35
     Masters
    0.35
     Workers
    0.35
     shelves
    0.35
    Activations Density 0.004%

    No Known Activations