© 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. 201409
    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_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
     as
    1.08
     W
    1.02
     by
    1.01
    have
    1.01
    há
    0.97
     C
    0.95
     B
    0.94
     wohl
    0.92
    ور
    0.90
    ing
    0.88
    POSITIVE LOGITS
    ۔
    1.21
    .
    0.98
    お金
    0.98
     дверей
    0.91
    ।
    0.91
     ресурсов
    0.86
    行う
    0.86
     مسلح
    0.85
     छात्रा
    0.84
     Jugendlichen
    0.82
    Activations Density 0.000%

    No Known Activations