© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84139
    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_23_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
     secretory
    0.49
     tumours
    0.45
    গঠনিক
    0.43
    nBitCount
    0.42
    oplasty
    0.42
     hepatocytes
    0.39
     العمليه
    0.39
    ▛
    0.39
     ހ
    0.39
     eluted
    0.39
    POSITIVE LOGITS
    ماش
    0.38
     Tr
    0.38
     Ter
    0.37
     cin
    0.37
     Tar
    0.36
    B
    0.36
     Did
    0.36
     **
    0.36
    2
    0.36
    kin
    0.35
    Activations Density 0.000%

    No Known Activations