© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210926
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_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
    on
    1.60
    ка
    1.51
    (
    1.43
     by
    1.38
    А
    1.38
    t
    1.32
    IT
    1.24
    PA
    1.22
    DA
    1.19
    ม
    1.19
    POSITIVE LOGITS
    ان
    1.25
     powied
    1.12
    یر
    1.08
     взя
    1.06
     сдела
    1.05
    였
    1.05
     сообщи
    1.03
     밝혔
    1.03
    sourced
    1.02
    descr
    1.01
    Activations Density 0.000%

    No Known Activations