© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57431
    Prev
    Next
    INDEX
    Explanations

    sign

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_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
     Config
    0.55
    ↵↵
    0.55
    maj
    0.54
     Endowment
    0.54
     Correspondent
    0.54
    💿
    0.52
    gm
    0.51
     款
    0.51
     工具
    0.51
    巾
    0.51
    POSITIVE LOGITS
    berapa
    0.59
    બ
    0.54
     fetched
    0.50
    образова
    0.50
     bolted
    0.49
     유
    0.49
    ження
    0.49
     surpassed
    0.49
     interestingly
    0.49
     Dương
    0.48
    Activations Density 0.035%

    No Known Activations