© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78516
    Prev
    Next
    INDEX
    Explanations

    file paths containing directories like src/kotlin/, src/main/, src/lib/, src/extension/

    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_31_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
     પટેલ
    0.43
     Nearby
    0.41
    nearby
    0.41
    чери
    0.40
     Displays
    0.40
     Foto
    0.39
    Nearby
    0.38
    妑
    0.38
    apest
    0.37
     বাধ
    0.36
    POSITIVE LOGITS
    स्यों
    0.44
     accessed
    0.40
    Problems
    0.38
     assign
    0.38
    操作
    0.36
    скоп
    0.36
     concerns
    0.35
     interpreters
    0.35
     шә
    0.35
    Опера
    0.35
    Activations Density 0.000%

    No Known Activations