© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217020
    Prev
    Next
    INDEX
    Explanations

    spatial placement (below, alongside, right)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    variables
    0.41
     variables
    0.40
    polygon
    0.37
    invokeLater
    0.36
     Bitter
    0.36
     conflit
    0.36
     Liet
    0.36
    즘
    0.36
    animation
    0.35
    #!/
    0.35
    POSITIVE LOGITS
     പൊ
    0.44
     बरसा
    0.42
     bestimmt
    0.40
     judul
    0.40
     बोल
    0.38
     पदाधिकारी
    0.38
     تعین
    0.38
     sulphide
    0.38
     स्वर्ण
    0.37
     veloce
    0.37
    Activations Density 0.002%

    No Known Activations