© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130248
    Prev
    Next
    INDEX
    Explanations

    integrals

    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_6_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
    是真的
    1.13
     współprac
    1.08
     won
    0.97
    -
    0.96
     вій
    0.95
     módulos
    0.95
    سكري
    0.94
     accommodate
    0.93
     gladly
    0.92
     detract
    0.91
    POSITIVE LOGITS
    Z
    1.03
    로
    0.90
    랑
    0.89
    R
    0.88
    لی
    0.86
    v
    0.86
    ção
    0.86
    ane
    0.84
    antar
    0.83
    H
    0.83
    Activations Density 0.000%

    No Known Activations