© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142399
    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_46_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
     menghub
    0.40
     뒷
    0.37
     Aware
    0.37
    imètres
    0.36
     Circles
    0.36
     ravel
    0.35
     organisation
    0.35
     memulai
    0.34
    何
    0.34
     یخ
    0.34
    POSITIVE LOGITS
    addAnimation
    0.38
    طع
    0.38
    巒
    0.37
    xes
    0.36
    чення
    0.36
    uated
    0.36
     thuật
    0.35
     Mansfield
    0.35
    플레이
    0.35
     செய்யுங்கள்
    0.34
    Activations Density 0.000%

    No Known Activations