© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66356
    Prev
    Next
    INDEX
    Explanations

    a fire upon the deep

    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_41_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
     geht
    0.42
    çado
    0.39
     बिंद
    0.36
     GPI
    0.36
    GPI
    0.36
     Ö
    0.35
     machinery
    0.35
     koe
    0.35
    inks
    0.35
    сын
    0.34
    POSITIVE LOGITS
    再來
    0.39
    куляр
    0.37
    ᱒
    0.37
     пробу
    0.36
    emar
    0.36
    自带
    0.36
    攀
    0.35
    icyclo
    0.35
    ানো
    0.35
     मार
    0.35
    Activations Density 0.001%

    No Known Activations