© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18395
    Prev
    Next
    INDEX
    Explanations

    Venice canals and Rialto

    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_15_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
    og
    0.61
    ore
    0.57
    d
    0.53
    ate
    0.50
    ib
    0.49
    ene
    0.48
    ocally
    0.47
    ob
    0.45
    ord
    0.45
    at
    0.45
    POSITIVE LOGITS
     борьбы
    0.56
    </strong>
    0.51
     борьбе
    0.51
     przyp
    0.49
    वणी
    0.49
     heli
    0.49
     termites
    0.48
     Informatika
    0.48
    ]।
    0.48
    ävät
    0.48
    Activations Density 0.002%

    No Known Activations