© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34747
    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_50_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
    числе
    0.40
    brad
    0.40
    savings
    0.38
     கட்சிய
    0.38
     கட்ச
    0.38
    ƣ
    0.37
    ("/{
    0.36
    Ge
    0.36
     Sultan
    0.36
    iqu
    0.36
    POSITIVE LOGITS
     pend
    0.42
     Collier
    0.40
    ೆಂಟ್
    0.39
     Mutter
    0.38
     있어
    0.37
     LIE
    0.37
    ឺ
    0.37
     নি
    0.37
     Nxf
    0.37
     शर्ट
    0.37
    Activations Density 0.000%

    No Known Activations