© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198159
    Prev
    Next
    INDEX
    Explanations

    language switches

    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_4_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
    ad
    0.95
     angios
    0.87
    쇤
    0.82
     thePack
    0.81
    お願い
    0.79
     aé
    0.79
     inept
    0.78
    ور
    0.78
    건
    0.77
     transonic
    0.77
    POSITIVE LOGITS
    ى
    1.09
    ين
    1.03
    ↵
    1.02
    ί
    0.95
    ната
    0.87
    l
    0.87
    i
    0.80
            
    0.79
    ку
    0.77
    </b>
    0.77
    Activations Density 0.000%

    No Known Activations