© 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. 163689
    Prev
    Next
    INDEX
    Explanations

    Apple A-series chips

    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
    c
    0.19
    col
    0.18
    marble
    0.17
    !
    0.17
    ،
    0.17
    IT
    0.17
    Switzerland
    0.17
    ƣ
    0.17
    न्व
    0.17
    ギー
    0.17
    POSITIVE LOGITS
    ويض
    0.19
     citado
    0.18
    ехал
    0.17
     bepaalde
    0.17
     folgende
    0.17
     Nesta
    0.17
     phải
    0.17
    скопа
    0.17
     meerdere
    0.17
    щем
    0.16
    Activations Density 0.003%

    No Known Activations