© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122800
    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_37_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
     уровне
    0.36
    尼亚
    0.36
    させて
    0.35
     寸
    0.35
    eteers
    0.34
    传说
    0.34
     rekom
    0.34
                        
    0.33
    Moz
    0.33
    ণীর
    0.33
    POSITIVE LOGITS
     otomatik
    0.45
    자동
    0.44
    alej
    0.40
     Copern
    0.40
    ുകയായിരുന്നു
    0.39
     Й
    0.39
     автомати
    0.38
     automatic
    0.38
     аўтаматы
    0.38
     federation
    0.37
    Activations Density 0.000%

    No Known Activations