© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225475
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    ত
    0.65
    ت
    0.65
    年
    0.55
     kereta
    0.54
    AH
    0.52
     godinu
    0.52
     menjel
    0.50
    ת
    0.50
     zak
    0.50
     vuoden
    0.49
    POSITIVE LOGITS
     ይጠ
    0.61
    ollen
    0.57
    
    0.56
    }_{+}
    0.55
    ]".
    0.54
    offre
    0.53
     அதிசயங்கள்
    0.53
     ଦ
    0.52
    ats
    0.50
    总量
    0.50
    Activations Density 0.000%

    No Known Activations