© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214886
    Prev
    Next
    INDEX
    Explanations

    CA or Ка

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     ?”
    0.43
    ⎯
    0.42
    ⣤
    0.37
    푸
    0.37
    運転
    0.37
     প্রণ
    0.37
    जो
    0.36
     پہنچ
    0.36
     Шта
    0.36
    profiles
    0.36
    POSITIVE LOGITS
    UV
    0.41
    र्च
    0.40
    acch
    0.40
    hemy
    0.39
    eg
    0.39
    uv
    0.38
     ac
    0.38
    ore
    0.38
     Chav
    0.38
    غ
    0.38
    Activations Density 0.000%

    No Known Activations