© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135756
    Prev
    Next
    INDEX
    Explanations

    teeth

    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_37_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
     orthodontic
    1.30
     orthodont
    1.21
     braces
    1.15
     dental
    1.05
     tooth
    1.04
     teeth
    1.00
     Invisalign
    0.94
    牙
    0.91
    Dental
    0.89
    tooth
    0.89
    POSITIVE LOGITS
     khúc
    0.46
    rello
    0.44
    屏
    0.39
    hém
    0.39
    핍
    0.38
     আঙ্গ
    0.36
    nahm
    0.36
    cliffe
    0.35
     लिपि
    0.35
    écran
    0.35
    Activations Density 0.014%

    No Known Activations