© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162568
    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_31_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
     filename
    0.43
     phosphorous
    0.40
    filename
    0.38
    යින්
    0.37
    Ⲡ
    0.37
    ឺ
    0.37
    ServiceName
    0.36
     চী
    0.36
     Mortgage
    0.36
    燐
    0.35
    POSITIVE LOGITS
    ek
    0.42
    Ket
    0.41
     Ket
    0.37
    Dr
    0.36
     ek
    0.36
    Ek
    0.36
    ak
    0.35
    woman
    0.35
    ket
    0.35
     Kassel
    0.35
    Activations Density 0.000%

    No Known Activations