© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207230
    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_46_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
    uição
    0.41
     નક્કી
    0.41
    shaw
    0.40
     vibration
    0.39
    CPM
    0.38
     vibrations
    0.38
     dźwię
    0.37
    縄
    0.37
     CPM
    0.37
    expectation
    0.37
    POSITIVE LOGITS
     needs
    0.47
     обладает
    0.46
     hates
    0.43
     posee
    0.41
     состоит
    0.41
     comporte
    0.41
     имеет
    0.41
     possesses
    0.41
     reacts
    0.40
    vercel
    0.40
    Activations Density 0.001%

    No Known Activations