© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 137444
    Prev
    Next
    INDEX
    Explanations

    sys.path

    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_37_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
     Texture
    0.46
     texture
    0.42
    ENV
    0.41
    叼
    0.38
     textures
    0.37
    Texture
    0.37
    στη
    0.37
     underage
    0.36
     homology
    0.36
     ENV
    0.35
    POSITIVE LOGITS
    unittest
    0.41
     kwargs
    0.41
     decorators
    0.39
     psycopg
    0.39
    Jour
    0.37
    픈
    0.37
    herald
    0.37
     छो
    0.37
    quired
    0.36
    ilst
    0.36
    Activations Density 0.000%

    No Known Activations