© 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. 204253
    Prev
    Next
    INDEX
    Explanations

    dance types and styles

    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
     dancer
    0.61
    dancer
    0.61
    Dancing
    0.61
    脚
    0.58
    Foot
    0.57
     dancing
    0.57
     Dancing
    0.55
    腳
    0.54
    Dance
    0.54
    foot
    0.54
    POSITIVE LOGITS
     solos
    0.43
     linear
    0.43
     pieces
    0.41
     Fron
    0.40
     duo
    0.40
     duet
    0.40
     sol
    0.39
     qualitative
    0.39
     Linear
    0.39
    线性
    0.39
    Activations Density 0.001%

    No Known Activations