© 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. 10327
    Prev
    Next
    INDEX
    Explanations

    numbers after punctuation

    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
     bet
    0.06
     often
    0.06
     source
    0.06
     barg
    0.06
     h
    0.05
     co
    0.05
     book
    0.05
    0.05
     ‘
    0.05
     female
    0.05
    POSITIVE LOGITS
     سایټ
    0.07
     Tjiwarl
    0.06
    жня
    0.06
     అవు
    0.06
     تړل
    0.06
    IsNull
    0.06
     Chipotle
    0.06
    흄
    0.06
    ukul
    0.06
     چاہئے
    0.06
    Activations Density 0.100%

    No Known Activations