© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 89154
    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_18_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
     EN
    0.48
    ])
    0.45
     EM
    0.38
     ให้
    0.38
    使用
    0.38
     Repert
    0.37
     xxx
    0.37
     ฝึก
    0.37
     Employ
    0.37
     C
    0.36
    POSITIVE LOGITS
     splatter
    0.45
    γι
    0.44
    jobs
    0.43
     cherries
    0.43
    ejs
    0.42
     curls
    0.42
     стабили
    0.42
    첼
    0.42
    暠
    0.41
    plotly
    0.41
    Activations Density 0.000%

    No Known Activations