© 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. 10072
    Prev
    Next
    INDEX
    Explanations

    Mixture of Experts (MoE)

    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
     IERC
    0.43
    0.42
    统治
    0.41
     presentaciones
    0.41
     moves
    0.41
     prohl
    0.40
    锅
    0.40
    <strong>
    0.39
     形
    0.39
    保留
    0.39
    POSITIVE LOGITS
    ्तर
    0.41
     оре
    0.41
    Kb
    0.38
    iv
    0.37
    Win
    0.37
     evade
    0.37
    Iv
    0.37
     wegen
    0.37
    к
    0.37
    kke
    0.36
    Activations Density 0.002%

    No Known Activations