© 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. 50905
    Prev
    Next
    INDEX
    Explanations

    swamps, fluctuating, step, deductibility, elements, manufacturers

    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
     proposte
    0.48
     proposto
    0.46
    举
    0.46
     Conquest
    0.46
     aquest
    0.46
     Veja
    0.46
     Equals
    0.45
     Sempre
    0.45
     tento
    0.45
     Increases
    0.44
    POSITIVE LOGITS
    ကို
    0.53
    bun
    0.47
     இருந்து
    0.46
    ນາ
    0.45
    በር
    0.45
    풉
    0.45
    ریٹر
    0.44
    DOF
    0.44
     سوری
    0.44
    ပို့
    0.44
    Activations Density 0.000%

    No Known Activations