© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6625
    Prev
    Next
    INDEX
    Explanations

    panic or panoramic

    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_40_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
     습
    0.37
    轪
    0.33
    流
    0.33
     Negro
    0.32
     шриф
    0.32
     shag
    0.32
     Đế
    0.32
    ەتی
    0.31
     Prend
    0.31
    =.
    0.31
    POSITIVE LOGITS
     panic
    2.27
     Panorama
    2.16
    panic
    2.13
     panoramic
    2.11
     panor
    2.11
    Panorama
    2.09
     panorama
    2.09
     Panic
    2.09
    Panic
    2.06
     PAN
    2.02
    Activations Density 0.103%

    No Known Activations