© 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. 84197
    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
     clearContext
    0.56
     strumento
    0.44
    视图
    0.44
     chúng
    0.43
     这里
    0.43
    优点
    0.42
     deseas
    0.42
    ༩
    0.42
     hiểu
    0.42
     Tsuen
    0.42
    POSITIVE LOGITS
     российских
    0.41
    nement
    0.40
     conformity
    0.40
    Russian
    0.39
    ร
    0.39
     injured
    0.38
    Okay
    0.38
    Belarus
    0.38
    Russia
    0.38
    Ін
    0.38
    Activations Density 0.000%

    No Known Activations