© 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. 36043
    Prev
    Next
    INDEX
    Explanations

    names

    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
    furn
    0.38
    Hydro
    0.37
     cinch
    0.37
     disponível
    0.37
    RNB
    0.37
     দীন
    0.37
    泡
    0.37
    RadioButton
    0.36
    हित
    0.36
    ਣ
    0.36
    POSITIVE LOGITS
     Qian
    0.50
     Yous
    0.47
     Morley
    0.47
     किसने
    0.45
     Mercy
    0.43
     Embry
    0.43
     Yarn
    0.43
     yì
    0.43
     Ya
    0.42
     Tengah
    0.42
    Activations Density 0.000%

    No Known Activations