© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200534
    Prev
    Next
    INDEX
    Explanations

    URLs and links

    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_50_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
    autical
    0.41
    zien
    0.39
    iczna
    0.37
    硃
    0.36
    auts
    0.36
    enzie
    0.36
    shaus
    0.36
     Guo
    0.35
     arrests
    0.35
    خان
    0.35
    POSITIVE LOGITS
     Rinse
    0.42
    enough
    0.38
     игровой
    0.38
     trộn
    0.36
    覺
    0.36
     InputListener
    0.36
     गेंद
    0.36
     kịp
    0.36
     Ingredient
    0.35
     শতাব্দীর
    0.35
    Activations Density 0.005%

    No Known Activations