© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27459
    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_40_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
    >∞</
    0.49
    ัฒ
    0.39
    Sci
    0.39
     Science
    0.37
    Science
    0.37
     flushed
    0.36
     ampliar
    0.35
    쫑
    0.35
     onChange
    0.35
    จร
    0.35
    POSITIVE LOGITS
    ޟ
    0.40
     `$
    0.39
    轻
    0.38
     procesos
    0.37
     CRUD
    0.36
    panel
    0.36
    國內
    0.36
    輕
    0.36
    出来
    0.35
     thôn
    0.35
    Activations Density 0.000%

    No Known Activations