© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 237535
    Prev
    Next
    INDEX
    Explanations

    mathematical comparisons and inequalities

    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_25_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
     ජී
    0.29
    ◡
    0.28
    စီး
    0.28
     ಸಾಕಷ್ಟು
    0.27
     ముఖ్య
    0.27
     شاء
    0.26
    隶
    0.26
     şek
    0.26
    SwingConstants
    0.26
    headless
    0.25
    POSITIVE LOGITS
     followed
    0.27
     increase
    0.27
     twin
    0.27
    п
    0.26
     expressed
    0.25
    രിച്ച
    0.25
     bumped
    0.25
    ribute
    0.25
     compounds
    0.25
     twinning
    0.25
    Activations Density 0.001%

    No Known Activations