© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8913
    Prev
    Next
    INDEX
    Explanations

    Pompeii and mosaics

    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_13_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
    N
    0.55
    github
    0.54
    Inverse
    0.49
    Sh
    0.49
    sh
    0.48
    Rés
    0.48
    })=\
    0.48
    UN
    0.47
    一
    0.47
    qat
    0.46
    POSITIVE LOGITS
     calcio
    0.57
     нещо
    0.57
     ltd
    0.53
     lujo
    0.53
     Ще
    0.52
     calle
    0.52
     Сти
    0.52
     deseo
    0.51
     attributing
    0.51
     ще
    0.50
    Activations Density 0.007%

    No Known Activations