© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245689
    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_40_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
    牀
    0.36
    摔
    0.35
     guarda
    0.35
    രായി
    0.35
    र्दू
    0.34
    ঙ্খ
    0.34
    硬盘
    0.34
     विष्णु
    0.33
     decap
    0.33
     रिकॉर्ड
    0.32
    POSITIVE LOGITS
     മൂ
    0.38
    Cra
    0.37
    aan
    0.35
    儁
    0.35
    四十
    0.35
     hub
    0.35
    zett
    0.35
     ROUILLER
    0.35
     bearer
    0.34
     অন্তর
    0.34
    Activations Density 0.000%

    No Known Activations