© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 98869
    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_16_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
     krank
    0.48
     dulce
    0.46
     Buscar
    0.46
     प्रि
    0.46
     ಯಾವುದೇ
    0.45
     Prozess
    0.44
    ष
    0.44
     Daha
    0.44
     cima
    0.44
     zum
    0.43
    POSITIVE LOGITS
    addPreferred
    0.47
     নাসির
    0.46
     Southampton
    0.46
    CTOGRAM
    0.46
    0.46
    Newcastle
    0.45
    avons
    0.44
    linkOpacity
    0.44
    ＮＡ
    0.42
     emigration
    0.42
    Activations Density 0.000%

    No Known Activations