© 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. 13385
    Prev
    Next
    INDEX
    Explanations

    balls and assault

    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
    ?
    0.25
     nécessaire
    0.23
    ？
    0.23
    ؟
    0.20
     árvore
    0.20
     für
    0.19
    :
    0.18
    zés
    0.18
     обнов
    0.18
     THEM
    0.18
    POSITIVE LOGITS
    ल्दी
    0.21
     generales
    0.20
    چال
    0.19
     صل
    0.19
    nsp
    0.18
    牝
    0.18
    trashItem
    0.18
     kadın
    0.18
    메
    0.18
     foresee
    0.17
    Activations Density 0.031%

    No Known Activations