© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15143
    Prev
    Next
    INDEX
    Explanations

    Disney Pixar movies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_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
     tubes
    0.39
    侖
    0.38
     ха
    0.37
     конститу
    0.36
     instabilities
    0.35
    핫
    0.35
    othic
    0.34
    </ul>
    0.34
    Woman
    0.34
     commission
    0.34
    POSITIVE LOGITS
     Pixar
    0.71
    ディズニー
    0.60
     Disney
    0.56
    迪士尼
    0.55
    Disney
    0.52
     Disneyland
    0.52
     DISNEY
    0.49
     disney
    0.46
     Walt
    0.43
    Walt
    0.41
    Activations Density 0.025%

    No Known Activations