© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9579
    Prev
    Next
    INDEX
    Explanations

    unnecessary, false, or spurious 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_13_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
    柇
    0.38
     भी
    0.38
    ự
    0.37
    rusty
    0.36
    ισμό
    0.36
    इस्
    0.35
     и
    0.35
    lions
    0.35
    ophobic
    0.35
     վ
    0.34
    POSITIVE LOGITS
     Fake
    0.42
     finalizar
    0.40
    ():
    0.39
     fake
    0.39
     Pseudo
    0.38
     pseudo
    0.37
     fictional
    0.37
     pseudonym
    0.36
    月号
    0.36
    for
    0.36
    Activations Density 0.179%

    No Known Activations