© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229525
    Prev
    Next
    INDEX
    Explanations

    left feeling a way

    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_57_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
     disgust
    0.45
    ,
    0.42
     catching
    0.40
     perception
    0.39
     smelling
    0.38
     &
    0.37
    ，
    0.37
    чен
    0.37
     leaving
    0.36
     पत्रिका
    0.36
    POSITIVE LOGITS
     यूनिवर्सल
    0.46
    Encycl
    0.41
     Changed
    0.39
     Isometric
    0.39
     വര്‍ഷ
    0.39
     Total
    0.39
    始
    0.38
     определенных
    0.38
     Ult
    0.38
     ക്
    0.38
    Activations Density 0.003%

    No Known Activations