© 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. 19354
    Prev
    Next
    INDEX
    Explanations

    fill with data

    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
    ✚
    0.54
    stellt
    0.52
    ⏎
    0.52
    enseignement
    0.52
    thisobject
    0.52
    ⓔ
    0.52
    ^*\
    0.52
     ScriptInterface
    0.52
    အစိတ်အပိုင်း
    0.51
    oplay
    0.51
    POSITIVE LOGITS
     data
    0.55
    ar
    0.54
    $
    0.52
     নিজেদের
    0.50
     U
    0.50
     sendiri
    0.49
     implementation
    0.48
     নিজের
    0.48
     offering
    0.48
     себя
    0.48
    Activations Density 0.006%

    No Known Activations