© 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. 199965
    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
    詹
    0.40
    阏
    0.39
     JAG
    0.39
     Jared
    0.38
     λ
    0.38
     lambda
    0.38
     FLU
    0.38
    λ
    0.37
    Flu
    0.37
    lambda
    0.37
    POSITIVE LOGITS
     reform
    3.08
     Reform
    2.91
    Reform
    2.91
    reform
    2.83
    改革
    2.69
     reforms
    2.64
     reforma
    2.59
     reformer
    2.53
     reformers
    2.52
     Reforms
    2.50
    Activations Density 0.000%

    No Known Activations