© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36214
    Prev
    Next
    INDEX
    Explanations

    visual disturbances

    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
    损
    0.46
    effort
    0.45
     effort
    0.41
    əm
    0.40
    压力
    0.40
    ალური
    0.39
    စည်း
    0.39
    壓力
    0.38
    損
    0.38
    仕事
    0.38
    POSITIVE LOGITS
     blinking
    0.49
     dizzy
    0.44
     wink
    0.41
     visions
    0.41
     মাদ
    0.40
     danced
    0.39
    朧
    0.39
     blinked
    0.38
     dancing
    0.38
     dizziness
    0.37
    Activations Density 0.035%

    No Known Activations