© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40951
    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_11_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
    ม
    0.58
     lipca
    0.56
     Atha
    0.54
     natomiast
    0.54
    ці
    0.52
    可能会
    0.52
    Ukrainian
    0.52
    𝗰
    0.52
    いろんな
    0.51
     Intense
    0.51
    POSITIVE LOGITS
    rolyte
    0.62
    ué
    0.58
    onat
    0.53
    et
    0.51
    erve
    0.50
     polygon
    0.49
     nuevas
    0.48
    estable
    0.48
     castle
    0.47
    ровку
    0.47
    Activations Density 0.000%

    No Known Activations