© 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. 4136
    Prev
    Next
    INDEX
    Explanations

    C standard library

    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
    assignments
    0.35
    womens
    0.29
     <%=
    0.29
     Assignments
    0.29
     Womens
    0.29
     mathematics
    0.29
     Mathematics
    0.28
    hardware
    0.28
     Dorm
    0.28
     Wool
    0.28
    POSITIVE LOGITS
     betrayal
    0.30
     ಅತ್ಯ
    0.30
     Вен
    0.29
    荚
    0.29
     deadliest
    0.29
     subscribed
    0.28
    ဆုံး
    0.27
     suscept
    0.27
    ጄ
    0.27
     disruption
    0.27
    Activations Density 0.002%

    No Known Activations