© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195726
    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_27_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
    TypeError
    0.41
    х
    0.40
    ми
    0.40
    м
    0.39
    раи
    0.39
    ස
    0.39
    Kim
    0.37
    线
    0.37
    强
    0.37
    Aligned
    0.37
    POSITIVE LOGITS
     Status
    0.37
     Greetings
    0.37
     Nevertheless
    0.36
     Listening
    0.36
     Todo
    0.35
     BEEN
    0.35
     constituer
    0.35
     Gö
    0.34
     Conseils
    0.34
     XVII
    0.34
    Activations Density 0.000%

    No Known Activations