© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30736
    Prev
    Next
    INDEX
    Explanations

    seventy and seven

    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
     WU
    0.37
    ৪
    0.36
    richTextBox
    0.35
    籌
    0.35
    нала
    0.35
     Ét
    0.34
    restricted
    0.34
    кому
    0.34
     refused
    0.34
     optimized
    0.34
    POSITIVE LOGITS
     seventy
    0.57
     Seventy
    0.56
     seven
    0.52
     bảy
    0.52
     семи
    0.52
    七
    0.51
     seventies
    0.50
     सात
    0.46
     ஏழு
    0.45
     Sevent
    0.45
    Activations Density 0.007%

    No Known Activations