© 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. 33220
    Prev
    Next
    INDEX
    Explanations

    2

    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
    그래서
    0.41
    ({"
    0.40
    hiyan
    0.39
    ••••
    0.39
    ("|"+"
    0.39
    कहां
    0.39
     (<
    0.38
     그래서
    0.37
     webbing
    0.37
    ={<
    0.37
    POSITIVE LOGITS
     enquiry
    0.38
     inquiry
    0.37
     obstáculos
    0.37
     derniers
    0.37
     perspekt
    0.37
    ₜ
    0.35
    Perspective
    0.35
     gấp
    0.34
     tertarik
    0.33
    트워크
    0.33
    Activations Density 0.009%

    No Known Activations