© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194729
    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_27_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
     worshipped
    0.45
     backed
    0.40
     silently
    0.38
    Backed
    0.38
    寜
    0.38
    塵
    0.37
     dü
    0.36
     kötü
    0.36
     sampah
    0.36
    ゴミ
    0.36
    POSITIVE LOGITS
     데
    0.40
     선정
    0.37
     postoperative
    0.36
    evaluate
    0.35
    특
    0.35
     कोशिका
    0.35
     оформ
    0.35
     Eurasia
    0.35
     assignments
    0.34
    评估
    0.34
    Activations Density 0.000%

    No Known Activations