© 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
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 56686
    Prev
    Next
    INDEX
    Explanations

    Google Play

    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_11_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
     for
    0.09
    ),
    0.09
    ));
    0.09
     whist
    0.09
     by
    0.09
    '
    0.08
     TER
    0.08
    )
    0.08
    ))
    0.08
    ة
    0.08
    POSITIVE LOGITS
     डेंगू
    0.10
    lining
    0.09
     Ingredients
    0.09
    ingredient
    0.09
    lingwood
    0.09
    lineContainer
    0.09
    trong
    0.09
    ogyakarta
    0.09
     कपड़ा
    0.09
    odge
    0.09
    Activations Density 0.006%

    No Known Activations