© 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. 216953
    Prev
    Next
    INDEX
    Explanations

    derivative antiderivative

    np_max-act-logits · gemini-2.5-flash-lite
    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
    鄧
    0.71
     DHS
    0.67
     DTS
    0.65
    邓
    0.64
     DCS
    0.63
     DFS
    0.63
     Dhar
    0.62
     dharm
    0.62
     DH
    0.60
     Dante
    0.60
    POSITIVE LOGITS
    嗪
    0.45
     absolue
    0.42
     সম্পূর্ন
    0.39
     khỏi
    0.38
    iguously
    0.38
    ویه
    0.38
    Ane
    0.38
    oweit
    0.38
    ouver
    0.37
     qualific
    0.37
    Activations Density 0.003%

    No Known Activations