© 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. 3705
    Prev
    Next
    INDEX
    Explanations

    types of accounts and records

    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
    ланы
    0.39
    lán
    0.37
     Melon
    0.37
     Inet
    0.36
     ยาก
    0.36
     bá
    0.36
    withtag
    0.35
    欖
    0.35
    san
    0.35
    榄
    0.35
    POSITIVE LOGITS
     benches
    0.41
     chatter
    0.39
     ১৫
    0.37
     ১৬
    0.37
    Workbench
    0.37
    ॐ
    0.36
    ानुसार
    0.36
    
    0.36
     فا
    0.35
     १५
    0.35
    Activations Density 0.020%

    No Known Activations