© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36010
    Prev
    Next
    INDEX
    Explanations

    project completion and construction

    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_31_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
    woofer
    0.39
     computational
    0.38
     صنعت
    0.38
    禁用
    0.38
    orsion
    0.38
     தொழில
    0.37
    化
    0.37
     upsetting
    0.37
     isopropyl
    0.36
     промышленности
    0.36
    POSITIVE LOGITS
     Completion
    0.50
     finishes
    0.50
    Completion
    0.48
     završ
    0.47
     권
    0.46
    úč
    0.42
     béton
    0.42
     شركة
    0.42
     Constructions
    0.42
     completion
    0.41
    Activations Density 0.004%

    No Known Activations