© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38032
    Prev
    Next
    INDEX
    Explanations

    D-Day or D-dimer

    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_3_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
    다
    0.71
    וס
    0.69
    誂
    0.69
     minimise
    0.67
    0.66
    ᅴ
    0.65
    jego
    0.64
     incentivize
    0.64
     എന്നാല്‍
    0.64
    )_{(
    0.60
    POSITIVE LOGITS
    0
    0.89
    ek
    0.84
    ink
    0.79
    ata
    0.75
     to
    0.73
     for
    0.73
     ett
    0.73
    ik
    0.70
    1
    0.70
    ick
    0.69
    Activations Density 0.003%

    No Known Activations