© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31551
    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_50_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
    zyc
    0.41
     وزار
    0.40
    फ्टर
    0.40
    呋
    0.38
    юк
    0.38
     फाय
    0.37
     kurul
    0.37
    }^{+}+\
    0.36
    furn
    0.36
    скими
    0.36
    POSITIVE LOGITS
    ethers
    0.37
    ப்பிர
    0.36
     objString
    0.36
     размеры
    0.36
     Telescope
    0.35
    Philadelphia
    0.35
     жөнүндө
    0.35
     Swim
    0.35
     Galle
    0.34
    javascript
    0.34
    Activations Density 0.000%

    No Known Activations