© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149827
    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_23_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
     emanc
    0.49
    锜
    0.47
    णाची
    0.46
    icore
    0.46
    iop
    0.45
    ட்சத்திர
    0.45
     endereço
    0.45
     wymaga
    0.45
     piè
    0.45
    สะดวก
    0.45
    POSITIVE LOGITS
     Leben
    0.44
     Vi
    0.44
    死
    0.44
     Swimming
    0.42
     య
    0.42
     కూడా
    0.42
    笑
    0.41
    到的
    0.41
     的
    0.40
    挑战
    0.39
    Activations Density 0.000%

    No Known Activations