© 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
    2. Gemma-3-27B-IT
    3. 39-GEMMASCOPE-2-TRANSCODER-262K
    4. 4605
    Prev
    Next
    INDEX
    Explanations

    ```python` context

    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_39_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
    elen
    0.45
    گاہ
    0.41
    v
    0.41
    iché
    0.41
     v
    0.40
    eten
    0.39
    onom
    0.38
     antif
    0.38
    shared
    0.38
     filthy
    0.37
    POSITIVE LOGITS
     ক্যান্টনমেন্ট
    0.39
     matematica
    0.39
    ACTIVITY
    0.37
     douceur
    0.37
     textvariable
    0.36
     пол
    0.36
     नवरा
    0.36
     Ples
    0.36
     GRAT
    0.35
    餡
    0.35
    Activations Density 0.000%

    No Known Activations