© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9592
    Prev
    Next
    INDEX
    Explanations

    string types

    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_13_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
     courants
    0.16
     lymphocytes
    0.15
    ᄆ
    0.15
     monomers
    0.14
    κει
    0.14
     epitopes
    0.14
    ய
    0.14
     които
    0.14
    ynı
    0.13
     एसपी
    0.13
    POSITIVE LOGITS
    io
    0.19
                  
    0.19
    il
    0.18
    ia
    0.18
    ↵
    0.17
                    
    0.16
    in
    0.16
                        
    0.16
    abhavena
    0.16
    vira
    0.16
    Activations Density 0.159%

    No Known Activations