© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58137
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    し
    1.29
     nėra
    1.13
     isang
    1.11
     ruas
    1.09
    の手
    1.05
     Organiz
    1.03
     Thành
    1.02
     aziende
    1.02
     Tujuan
    1.02
    の間
    1.01
    POSITIVE LOGITS
    ة
    2.38
    ing
    1.76
    9
    1.73
    5
    1.71
    7
    1.69
    6
    1.63
    8
    1.62
    .
    1.45
    4
    1.43
     by
    1.35
    Activations Density 0.000%

    No Known Activations