© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132085
    Prev
    Next
    INDEX
    Explanations

    say "i" words

    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
     исклю
    0.45
    лович
    0.40
     excludes
    0.40
     chimique
    0.39
     Hannibal
    0.39
     バイ
    0.38
     nisi
    0.38
    빗
    0.38
    ley
    0.37
    Loan
    0.37
    POSITIVE LOGITS
     বর্ধ
    0.43
    جد
    0.41
     செல்வ
    0.40
    aros
    0.39
    duck
    0.38
    discussed
    0.38
    зара
    0.38
    race
    0.38
    zal
    0.38
    jdk
    0.37
    Activations Density 0.005%

    No Known Activations