© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 218614
    Prev
    Next
    INDEX
    Explanations

    vernier calipers, Folsom Prison, Prometheus, Types, excited

    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_16_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
      
    0.56
          
    0.55
     is
    0.55
             
    0.53
     has
    0.52
    in
    0.51
    u
    0.51
                 
    0.50
     extracted
    0.50
     For
    0.50
    POSITIVE LOGITS
    ку
    0.60
    ři
    0.58
    ří
    0.56
    čí
    0.56
    ції
    0.55
    рами
    0.54
    ્રે
    0.54
    ствующие
    0.54
     artística
    0.53
    ър
    0.53
    Activations Density 0.000%

    No Known Activations