© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214939
    Prev
    Next
    INDEX
    Explanations

    Works, AppWorks, Stahlwerker, Logic

    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_5_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
    ו
    1.38
    im
    1.35
    at
    1.33
    3
    1.24
    大
    1.17
    การ
    1.16
    ك
    1.12
    是
    1.10
    方法
    1.09
    2
    1.08
    POSITIVE LOGITS
    ;
    0.89
    ک
    0.87
    kenalkan
    0.85
    )
    0.84
    nya
    0.84
    ानी
    0.83
     diffeomorphism
    0.79
    หรับ
    0.78
    स
    0.78
     adversaries
    0.75
    Activations Density 0.000%

    No Known Activations