© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204376
    Prev
    Next
    INDEX
    Explanations

    Tooth

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     tooth
    1.31
     Tooth
    1.10
    Tooth
    1.10
    tooth
    1.05
    牙
    0.80
     зуб
    0.72
    歯
    0.71
     teeth
    0.63
     dental
    0.62
     răng
    0.59
    POSITIVE LOGITS
    ‰
    0.48
    äte
    0.41
    runk
    0.39
    бар
    0.39
     Hy
    0.39
    BURTS
    0.39
    pase
    0.39
     hy
    0.38
    gave
    0.38
     Hyde
    0.38
    Activations Density 0.000%

    No Known Activations