© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172794
    Prev
    Next
    INDEX
    Explanations

    takes into account

    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_20_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
     portfolio
    0.24
    тім
    0.24
     seizure
    0.22
    ซ
    0.22
    Methods
    0.22
    Референце
    0.21
     черный
    0.21
     ዘዴ
    0.21
    Decre
    0.21
    贞
    0.21
    POSITIVE LOGITS
     mellom
    0.25
              
    0.24
     zwischen
    0.24
    Durante
    0.24
            
    0.23
     Cortez
    0.23
    imamente
    0.23
     mellan
    0.22
     Giappone
    0.22
    船
    0.22
    Activations Density 0.007%

    No Known Activations