© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87570
    Prev
    Next
    INDEX
    Explanations

    subplot"

    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_23_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
    ة
    0.46
     interes
    0.46
    ंजी
    0.44
    لا
    0.43
    不
    0.43
    埙
    0.43
    管理
    0.42
    职
    0.42
    olt
    0.41
    Community
    0.41
    POSITIVE LOGITS
     arguably
    0.47
     wildlife
    0.46
     magenta
    0.45
     telecoms
    0.44
     ร่วม
    0.44
     waterfowl
    0.43
    UCK
    0.43
     waterways
    0.43
     pledging
    0.42
     scoff
    0.42
    Activations Density 0.000%

    No Known Activations