© 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. 9776
    Prev
    Next
    INDEX
    Explanations

    aberrations, Lagrange invariant, electrons, circle

    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
    ｅ
    0.46
    rées
    0.44
     Guide
    0.43
     Agriculture
    0.42
    w
    0.42
    yn
    0.42
     présents
    0.42
     Traditions
    0.42
    绯
    0.42
    记忆
    0.42
    POSITIVE LOGITS
     refracting
    0.56
     торго
    0.47
     сум
    0.47
    ITER
    0.47
    ACE
    0.47
    вався
    0.47
     расши
    0.46
     živ
    0.46
     согласо
    0.46
    镞
    0.46
    Activations Density 0.009%

    No Known Activations