© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155408
    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_50_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
    江
    0.43
    Lei
    0.42
     Cơ
    0.40
     नदियों
    0.40
    δια
    0.38
    lei
    0.38
    дания
    0.38
    Jiang
    0.38
    滀
    0.38
     utak
    0.38
    POSITIVE LOGITS
    HJ
    0.44
     HJ
    0.41
     reaper
    0.39
    هِ
    0.39
    SB
    0.39
    nj
    0.38
     AJ
    0.38
     PJ
    0.38
     herz
    0.38
     BJ
    0.37
    Activations Density 0.000%

    No Known Activations