© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 3862
    Prev
    Next
    INDEX
    Explanations

    chat prompts

    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_38_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
    цэ
    0.47
    Meter
    0.41
    usa
    0.40
    othesis
    0.39
     গম
    0.39
    idé
    0.38
    .*\
    0.38
     सिरसा
    0.37
    仙台
    0.37
    魧
    0.37
    POSITIVE LOGITS
    אה
    0.42
     полю
    0.40
     ইলেক্ট্রোলাই
    0.38
     পরস্প
    0.38
     passion
    0.36
     hostname
    0.36
     videojuegos
    0.36
     Gameplay
    0.35
     Kaitlyn
    0.35
     creator
    0.35
    Activations Density 0.002%

    No Known Activations