© 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
    2. Gemma-3-27B-IT
    3. 39-GEMMASCOPE-2-TRANSCODER-262K
    4. 4092
    Prev
    Next
    INDEX
    Explanations

    youyou ' or you can

    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_39_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
     tonnage
    0.42
     Veuillez
    0.42
     Migration
    0.40
     Metadata
    0.40
     Connections
    0.38
    彆
    0.38
     terminology
    0.38
     Seth
    0.38
     Mô
    0.38
     Использу
    0.37
    POSITIVE LOGITS
    iders
    0.39
     festge
    0.39
     instigated
    0.39
    hauser
    0.38
     предостав
    0.38
     Ecusson
    0.38
    inien
    0.38
    盜
    0.38
     grabbed
    0.37
     fournis
    0.37
    Activations Density 0.154%

    No Known Activations