© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 203728
    Prev
    Next
    INDEX
    Explanations

    multi-part concepts

    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
    Negative Logits
    gur
    0.48
    servers
    0.46
    gern
    0.45
     crazy
    0.43
    ghe
    0.42
    igslist
    0.41
    gomery
    0.41
    gor
    0.41
    g
    0.40
    gus
    0.39
    POSITIVE LOGITS
    ed
    0.59
    ี
    0.39
    ุ่ม
    0.39
    ituary
    0.36
     Properly
    0.35
    ˄
    0.35
    subscription
    0.34
    en
    0.34
    setShow
    0.34
    ִ
    0.33
    Activations Density 0.034%

    No Known Activations