© 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. 50305
    Prev
    Next
    INDEX
    Explanations

    sentence terminators followed by diverse topics

    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
    zant
    0.32
    Judge
    0.30
          
    0.29
    aplic
    0.29
    zet
    0.29
     Î
    0.29
     bhave
    0.28
     apl
    0.28
    namese
    0.28
     தாக்க
    0.28
    POSITIVE LOGITS
     آنچه
    0.36
    人們
    0.34
    ْن
    0.31
     empires
    0.31
    祂
    0.30
    空氣
    0.30
    注意到
    0.29
     Beyond
    0.28
     heavens
    0.28
    retching
    0.28
    Activations Density 0.000%

    No Known Activations