© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63574
    Prev
    Next
    INDEX
    Explanations

    rotor

    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_41_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
     ζ
    0.42
    unittest
    0.41
    裤
    0.41
     Catherine
    0.40
    Catherine
    0.39
     Carnegie
    0.39
     επέ
    0.38
    канчи
    0.37
    )^{-
    0.36
     Monarch
    0.36
    POSITIVE LOGITS
     rotor
    2.16
     rotors
    1.94
     Rotor
    1.93
    rotor
    1.87
     helicopter
    1.30
     helicopters
    1.16
     rot
    1.16
     Rot
    1.14
    rot
    1.08
    Rot
    1.08
    Activations Density 0.004%

    No Known Activations