© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177361
    Prev
    Next
    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Pistol
    0.45
     fortr
    0.41
    诲
    0.40
    daad
    0.38
     veze
    0.38
     發
    0.37
    <unused16>
    0.37
    вих
    0.37
    狨
    0.37
    囵
    0.36
    POSITIVE LOGITS
     कैल
    0.41
     Inca
    0.38
     Xanth
    0.38
    ίν
    0.37
     Bif
    0.36
    }^{[
    0.36
     лица
    0.36
    ridium
    0.36
    slideTo
    0.36
    葵
    0.36
    Activations Density 0.000%

    No Known Activations