© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87855
    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
     sahab
    0.48
     Laurent
    0.42
     Сасик
    0.41
     mày
    0.40
    :")
    0.40
    MyToolkit
    0.40
    ştik
    0.38
    ༘
    0.38
    kiye
    0.38
    naye
    0.38
    POSITIVE LOGITS
    す
    0.40
    нова
    0.38
    決
    0.38
    vert
    0.37
    for
    0.36
     О
    0.36
    ler
    0.34
    雨
    0.34
    ビル
    0.34
     receber
    0.33
    Activations Density 0.000%

    No Known Activations