© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169058
    Prev
    Next
    INDEX
    Explanations

    lot

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     fed
    0.40
    appeared
    0.39
     left
    0.38
     planned
    0.37
    
    0.37
    Fed
    0.37
     quedaron
    0.37
     pesar
    0.37
    左
    0.36
     során
    0.35
    POSITIVE LOGITS
     dependant
    0.49
     dependents
    0.48
     Dependent
    0.46
    dependent
    0.45
     dependent
    0.45
     vận
    0.41
    opal
    0.41
    Dependent
    0.41
     comparisons
    0.40
     зависи
    0.40
    Activations Density 0.003%

    No Known Activations