© 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. 162973
    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
    AreEqual
    0.42
     gara
    0.42
    ዦ
    0.42
    istiwa
    0.39
    auxite
    0.36
     انتقال
    0.36
     bekas
    0.36
     হস্তান্তর
    0.35
    ANGE
    0.35
     murals
    0.35
    POSITIVE LOGITS
     தமி
    0.44
     Kins
    0.38
     receta
    0.38
     conseil
    0.38
     ""}
    0.38
     pug
    0.37
     Jays
    0.37
     امریکی
    0.36
     perspectiva
    0.36
     AI
    0.35
    Activations Density 0.000%

    No Known Activations