© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7628
    Prev
    Next
    INDEX
    Explanations

    charge separation and resonant tunneling

    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_40_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
    ினம்
    0.36
     विचारों
    0.35
     সাব
    0.34
    保养
    0.33
    꽉
    0.33
     seizures
    0.32
     स्टॉक
    0.32
    chromiumfx
    0.32
    耱
    0.32
     ग्वालियर
    0.31
    POSITIVE LOGITS
     behavior
    0.43
    行为
    0.40
     Behavior
    0.39
    aux
    0.38
     कंडी
    0.37
    ้า
    0.36
    behavior
    0.35
     поведение
    0.34
    Behavior
    0.34
    แห
    0.34
    Activations Density 0.019%

    No Known Activations