© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 68928
    Prev
    Next
    INDEX
    Explanations

    say "p" 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_51_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
     rescu
    0.44
     ServicePolicy
    0.42
    룸
    0.38
    PARAMETERS
    0.38
     يزيد
    0.36
     rescat
    0.36
     উদ্দেশ
    0.35
    Tür
    0.35
    Ong
    0.34
    obraz
    0.34
    POSITIVE LOGITS
     лег
    1.53
     лёг
    1.31
     light
    1.08
    轻
    1.08
    輕
    1.08
     légère
    1.02
    軽
    1.00
     轻
    0.98
     Light
    0.97
     hafif
    0.96
    Activations Density 0.002%

    No Known Activations