© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200474
    Prev
    Next
    INDEX
    Explanations

    up

    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_46_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
     fuoco
    0.38
    ieu
    0.38
     hame
    0.38
    坌
    0.38
    breaker
    0.38
    hame
    0.37
    gap
    0.37
     Crucible
    0.36
    H
    0.36
    mite
    0.36
    POSITIVE LOGITS
     up
    0.61
     Up
    0.54
     upto
    0.51
    起来
    0.49
     lên
    0.48
    Up
    0.46
    起來
    0.42
     Valencia
    0.42
     karte
    0.40
    ขึ้น
    0.40
    Activations Density 0.001%

    No Known Activations