© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35140
    Prev
    Next
    INDEX
    Explanations

    tallest building in Paris

    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_31_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
     Jersey
    0.46
    Jersey
    0.45
     поме
    0.42
    fordshire
    0.41
    jersey
    0.41
     측
    0.40
     langchain
    0.38
     Guernsey
    0.38
     jersey
    0.36
     override
    0.36
    POSITIVE LOGITS
    餾
    0.37
    áf
    0.35
     Ages
    0.35
     UPSC
    0.35
    akh
    0.34
     paroi
    0.34
    benef
    0.34
    rotto
    0.34
    Simulator
    0.34
    pia
    0.34
    Activations Density 0.018%

    No Known Activations