© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 121474
    Prev
    Next
    INDEX
    Explanations

    nostrils flare

    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_38_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
    Sheffield
    0.46
    禊
    0.41
    рои
    0.41
     inhibition
    0.40
    <unused0>
    0.39
     ше
    0.39
     linguistic
    0.39
     Sheffield
    0.38
     deportation
    0.38
    idemargin
    0.38
    POSITIVE LOGITS
     nostrils
    1.05
     nost
    0.96
     nasal
    0.93
    鼻
    0.86
     Nost
    0.82
    nost
    0.78
     nose
    0.71
     Nose
    0.69
    콧
    0.68
     noses
    0.65
    Activations Density 0.004%

    No Known Activations