© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84002
    Prev
    Next
    INDEX
    Explanations

    piano music and performance

    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_0_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
    ่
    1.44
    ру
    1.41
    не
    1.34
    ло
    1.32
     I
    1.29
    发展
    1.24
     renormal
    1.24
    ту
    1.16
    ι
    1.16
    值
    1.14
    POSITIVE LOGITS
    t
    2.05
    ため
    1.66
    f
    1.51
    ために
    1.48
    dır
    1.44
     in
    1.39
    ac
    1.39
     that
    1.33
    g
    1.33
    gli
    1.27
    Activations Density 0.001%

    No Known Activations