© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215034
    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_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
     hola
    0.39
     Kole
    0.39
     Nile
    0.38
     Noah
    0.38
    קה
    0.37
    LEGISLATIVE
    0.37
    屐
    0.37
     kapcs
    0.37
     коллек
    0.37
     কালে
    0.36
    POSITIVE LOGITS
     ICU
    0.37
     canyon
    0.37
     عرض
    0.36
     labyrinth
    0.36
    AVC
    0.35
    edo
    0.35
    edt
    0.35
    E
    0.35
     enn
    0.35
    cheng
    0.34
    Activations Density 0.000%

    No Known Activations