© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74891
    Prev
    Next
    INDEX
    Explanations

    low effort/low reward

    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_31_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
     orders
    0.42
    сро
    0.42
    Late
    0.39
    Та
    0.38
    Essay
    0.37
    進
    0.37
    городе
    0.36
     late
    0.36
    orders
    0.36
    Orders
    0.35
    POSITIVE LOGITS
    ၞ
    0.37
     prévu
    0.34
     david
    0.34
    čná
    0.34
     നേതൃ
    0.33
     prévue
    0.33
    阻
    0.33
     ځای
    0.33
    vegarde
    0.33
     peralatan
    0.33
    Activations Density 0.002%

    No Known Activations