© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57944
    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_59_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
     UK
    0.89
     Uk
    0.86
     uk
    0.76
    UK
    0.73
    Uk
    0.64
     Укра
    0.64
     укра
    0.64
     U
    0.55
    uk
    0.52
     You
    0.49
    POSITIVE LOGITS
    Bt
    0.44
    hashMap
    0.40
    express
    0.40
    bt
    0.39
    unsqueeze
    0.39
    Sx
    0.38
    japanese
    0.37
    CHARACTER
    0.37
     PROGRAM
    0.37
    Database
    0.37
    Activations Density 0.000%

    No Known Activations