© 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. 166467
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    醃
    0.41
    突破
    0.38
    Breakpoint
    0.38
    隨
    0.37
     ৫১
    0.37
    Mileage
    0.35
     Break
    0.35
    軚
    0.35
    稳定性
    0.34
    随
    0.34
    POSITIVE LOGITS
    AKE
    0.49
     scattered
    0.45
     opposing
    0.43
    scatter
    0.42
     oppon
    0.40
    竞争
    0.39
     enemies
    0.39
     purus
    0.39
    acate
    0.38
    refresh
    0.38
    Activations Density 0.000%

    No Known Activations