© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40496
    Prev
    Next
    INDEX
    Explanations

    equestrian and riding terms

    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_11_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
    ían
    0.51
    ados
    0.49
    odore
    0.48
     ngan
    0.47
    
    0.47
    ocos
    0.46
    gan
    0.46
    ade
    0.45
     نه
    0.45
    மி
    0.45
    POSITIVE LOGITS
     equestrian
    0.54
     lông
    0.54
     horseback
    0.53
     paddock
    0.52
     Règ
    0.49
     motoc
    0.48
    Horse
    0.48
     Riding
    0.48
    {~
    0.46
     ducks
    0.46
    Activations Density 0.024%

    No Known Activations