© 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. 6348
    Prev
    Next
    INDEX
    Explanations

    World War II and roman numerals

    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
    റാ
    0.37
    DETECT
    0.36
    ﮩ
    0.34
     französischen
    0.34
    0.33
     कनेक्टिव
    0.33
     প্রমাণ
    0.32
     rinnov
    0.32
     diber
    0.32
     financement
    0.32
    POSITIVE LOGITS
     II
    0.71
    II
    0.61
     III
    0.59
    Ⅲ
    0.59
    Ⅱ
    0.58
    III
    0.53
     IV
    0.52
    Ⅳ
    0.48
     ii
    0.47
    Ⅰ
    0.47
    Activations Density 0.090%

    No Known Activations