© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218316
    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_31_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
     logo
    0.38
    **
    0.36
     raind
    0.35
     Honors
    0.35
    โรค
    0.34
     बराम
    0.34
    இந்நிலையில்
    0.34
    rophot
    0.33
    oyant
    0.33
     Hochschule
    0.33
    POSITIVE LOGITS
    pall
    0.38
    ষ্ট
    0.37
     каких
    0.37
    リス
    0.36
     ރ
    0.36
    LiveData
    0.36
    管理人
    0.35
     управ
    0.35
     méridionale
    0.34
     управля
    0.34
    Activations Density 0.000%

    No Known Activations