© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98293
    Prev
    Next
    INDEX
    Explanations

    auction houses and art prices

    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_14_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
    би
    0.51
    usso
    0.50
     н
    0.47
    лд
    0.47
    восто
    0.47
     ил
    0.46
     Según
    0.46
     según
    0.46
    следова
    0.46
    lact
    0.46
    POSITIVE LOGITS
     அறிக
    0.62
    ories
    0.53
     construction
    0.49
     dumb
    0.49
     isn
    0.48
    ელია
    0.48
    ).__
    0.48
     webbing
    0.48
     doesn
    0.48
     insufficiently
    0.47
    Activations Density 0.000%

    No Known Activations