© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207426
    Prev
    Next
    INDEX
    Explanations

    code structure markers

    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_19_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
    芾
    0.19
    यद
    0.17
     vấn
    0.17
     ngân
    0.16
     gula
    0.16
     ай
    0.16
    央
    0.16
     grom
    0.16
    ڦ
    0.16
    шот
    0.16
    POSITIVE LOGITS
     Ez
    0.19
    rows
    0.19
    cer
    0.18
    ola
    0.18
    keys
    0.18
    ca
    0.18
    azem
    0.18
     El
    0.18
    tex
    0.18
    c
    0.18
    Activations Density 0.000%

    No Known Activations