© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177520
    Prev
    Next
    INDEX
    Explanations

    application process

    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_24_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
    Vox
    0.43
    台
    0.43
    вої
    0.42
    Glass
    0.41
    Memory
    0.40
    Gesellschaft
    0.38
    Terra
    0.38
     जेटली
    0.38
    Das
    0.38
    لوب
    0.38
    POSITIVE LOGITS
     ज्ञात
    0.48
     निर्धारित
    0.45
     abide
    0.44
    🍠
    0.43
     ကျွန်
    0.41
     விட்டு
    0.40
     விதி
    0.40
    ➚
    0.40
     आवृत्ति
    0.39
     규칙
    0.39
    Activations Density 0.000%

    No Known Activations