© 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. 32257
    Prev
    Next
    INDEX
    Explanations

    locations or entities

    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
     गोपाल
    0.41
    πος
    0.39
    messageInfo
    0.39
    עות
    0.38
     Northeastern
    0.37
    ᚄ
    0.36
     northeastern
    0.36
    romes
    0.35
    arlene
    0.35
     пай
    0.35
    POSITIVE LOGITS
     Anand
    0.47
    hole
    0.46
     hole
    0.46
    addHandler
    0.43
     Ha
    0.42
     forwarded
    0.41
     Pelican
    0.40
    蛍
    0.40
    дування
    0.40
     હા
    0.40
    Activations Density 0.004%

    No Known Activations