© 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. 202929
    Prev
    Next
    INDEX
    Explanations

    nose

    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
     pharmacokinetic
    0.37
    ...")
    0.37
     analy
    0.36
     Glyph
    0.36
     Focal
    0.35
     desta
    0.35
    ధి
    0.35
    制
    0.35
     ہوگا۔
    0.35
     immersion
    0.34
    POSITIVE LOGITS
     nose
    0.50
     Nose
    0.49
    nose
    0.49
     liner
    0.44
     noses
    0.42
    сное
    0.41
    nosed
    0.41
    ba
    0.40
    Tomas
    0.39
    Aes
    0.39
    Activations Density 0.044%

    No Known Activations