© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 178799
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    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_29_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
     aka
    0.54
     अर्थात
    0.41
     (
    0.41
     (_
    0.40
     AKA
    0.40
     yani
    0.39
     refer
    0.39
     Refer
    0.38
     moniker
    0.36
     stretchy
    0.36
    POSITIVE LOGITS
    دانلود
    0.38
    кмекер
    0.38
    一是
    0.38
     Simply
    0.37
     زمین
    0.37
    걍
    0.37
    珵
    0.36
     jednostavno
    0.36
    Acknowledg
    0.36
     Lough
    0.36
    Activations Density 0.001%

    No Known Activations