© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 211904
    Prev
    Next
    INDEX
    Explanations

    `"` or `'` followed by `{` or `(`

    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_19_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
     بیمار
    0.50
     errorMessage
    0.46
     경우에는
    0.45
     любую
    0.45
     qualsiasi
    0.45
     paramètres
    0.45
    𒄩
    0.45
     mùi
    0.44
     ಅವನ
    0.44
    ální
    0.43
    POSITIVE LOGITS
    <blockquote>
    0.46
    ommen
    0.40
    眠
    0.40
     strobe
    0.40
     They
    0.39
     parted
    0.38
     Tonight
    0.38
     सशस्त्र
    0.37
     sprung
    0.36
     Whitehall
    0.36
    Activations Density 0.001%

    No Known Activations