© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 81738
    Prev
    Next
    INDEX
    Explanations

    list item headings

    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
    <code>
    0.40
    crew
    0.39
     $\
    0.38
    7
    0.36
    6
    0.36
     Cristo
    0.35
    soap
    0.35
     totalling
    0.35
    <
    0.35
    ocrat
    0.35
    POSITIVE LOGITS
    ژه
    0.44
    <unused48>
    0.43
     ਕਰ
    0.39
    जेक्ट
    0.38
    рованным
    0.38
    ශ්‍ය
    0.38
     schak
    0.37
    attiyam
    0.37
     Подо
    0.36
     अनुशंसा
    0.36
    Activations Density 0.002%

    No Known Activations