© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198675
    Prev
    Next
    INDEX
    Explanations

    indicate helpful information

    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_15_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
     Découvrez
    0.39
    <unused973>
    0.38
     متا
    0.38
     နောက်
    0.38
    maat
    0.38
     なさい
    0.37
    odynam
    0.37
     ठेवा
    0.37
     quirúrg
    0.37
     Quellen
    0.37
    POSITIVE LOGITS
     constantly
    0.39
    以
    0.39
    常
    0.39
    Corn
    0.38
    const
    0.38
     corn
    0.37
    with
    0.36
    在
    0.35
     reactivation
    0.35
    ς
    0.35
    Activations Density 0.047%

    No Known Activations