© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200679
    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_12_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
     zasi
    0.57
     μία
    0.56
    を中心に
    0.55
    ভিত্তিক
    0.55
    യിരുന്നു
    0.52
    スの
    0.50
     ширина
    0.50
    <unused584>
    0.50
     sosok
    0.50
     ücretsiz
    0.50
    POSITIVE LOGITS
    rag
    0.56
     Title
    0.54
     Deals
    0.54
    设立
    0.54
    ril
    0.53
     undetectable
    0.53
    куляр
    0.51
    iod
    0.49
    rishnan
    0.49
    iov
    0.49
    Activations Density 0.000%

    No Known Activations