© 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. 178536
    Prev
    Next
    INDEX
    Explanations

    one followed by for, to, with, or in

    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
     consists
    0.43
    اءِ
    0.42
     enables
    0.38
     obedience
    0.38
    極
    0.38
    porto
    0.38
    MY
    0.37
     কাজের
    0.37
    ِلِّ
    0.37
     আবেদনের
    0.36
    POSITIVE LOGITS
    ๒
    0.43
     aho
    0.37
    тні
    0.37
     tại
    0.37
    тэй
    0.36
    ،
    0.36
    \"
    0.35
    涫
    0.35
     среди
    0.35
    ᴱ
    0.34
    Activations Density 0.002%

    No Known Activations