© 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. 167112
    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
    هرات
    0.39
     procès
    0.37
    reonine
    0.37
     asesinato
    0.37
     attached
    0.36
    飲み
    0.35
    挿
    0.34
     analysis
    0.34
     IOException
    0.33
     vanishing
    0.33
    POSITIVE LOGITS
    、​
    0.41
     MAKEINTRESOURCE
    0.39
    乆
    0.39
    헴
    0.38
     뭘
    0.38
     angka
    0.37
     استف
    0.37
    delen
    0.36
    apd
    0.36
    작
    0.36
    Activations Density 0.000%

    No Known Activations