© 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. 242952
    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
    单元
    0.43
     стиля
    0.43
     STYLE
    0.41
    风格
    0.38
     стиль
    0.38
    LEC
    0.38
     fifteenth
    0.37
    😃
    0.37
    Reduction
    0.37
    しくて
    0.37
    POSITIVE LOGITS
     Dol
    0.39
     Nicholson
    0.38
    嫩
    0.37
     dollar
    0.36
     дол
    0.36
    Dollar
    0.36
    out
    0.35
     hollow
    0.35
     dors
    0.35
     डिसेंबर
    0.35
    Activations Density 0.000%

    No Known Activations