© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 207059
    Prev
    Next
    INDEX
    Explanations

    labor

    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_10_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
    e
    0.19
    Find
    0.19
    à
    0.18
    More
    0.18
    u
    0.18
    百
    0.18
    f
    0.18
    or
    0.18
     to
    0.17
    Peer
    0.17
    POSITIVE LOGITS
    ı
    0.20
     설계
    0.20
     dezvolt
    0.19
     discussão
    0.19
     revisão
    0.19
     precum
    0.19
    캘
    0.19
    ﷲ
    0.19
    ılar
    0.19
     sağlam
    0.19
    Activations Density 0.006%

    No Known Activations