© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1835
    Prev
    Next
    INDEX
    Explanations

    .NET Framework and versions

    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_39_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
    athletics
    0.40
    ben
    0.38
    名古屋
    0.38
    uron
    0.38
    лист
    0.38
     રહી
    0.38
     कमाने
    0.37
    侍
    0.37
    crawl
    0.37
     कमाए
    0.36
    POSITIVE LOGITS
     Büh
    0.38
    ेंद
    0.37
    ittances
    0.36
    晁
    0.36
     Centrale
    0.35
     সম্ব
    0.35
     बृहस्पतिवार
    0.35
     belief
    0.35
     bureaux
    0.35
     promenade
    0.34
    Activations Density 0.009%

    No Known Activations