© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 203767
    Prev
    Next
    INDEX
    Explanations

    hasattr/getattr calls

    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
     upside
    0.38
    Melissa
    0.38
    磕
    0.38
     Melissa
    0.38
     அபி
    0.37
     explos
    0.36
     intrinsic
    0.36
     explosive
    0.36
     intrat
    0.36
     பிரி
    0.36
    POSITIVE LOGITS
    ियर
    0.39
     обна
    0.38
    CloseOperation
    0.37
    鐺
    0.37
     ausge
    0.35
    -'].
    0.35
    ায়ণের
    0.34
    ]].
    0.33
    怠
    0.32
    تك
    0.32
    Activations Density 0.000%

    No Known Activations