© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43959
    Prev
    Next
    INDEX
    Explanations

    placeholders for formal address

    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_22_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
    환
    0.21
    水平
    0.20
     dietary
    0.20
    Fecha
    0.19
     fecha
    0.19
     Fecha
    0.19
     สัก
    0.19
    年
    0.18
    物品
    0.18
     godine
    0.18
    POSITIVE LOGITS
    celli
    0.23
     Logistics
    0.23
    澧
    0.22
     adventures
    0.22
    ategy
    0.21
     championed
    0.21
     complex
    0.21
     Padre
    0.21
     жизни
    0.21
     Party
    0.21
    Activations Density 0.004%

    No Known Activations