© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5728
    Prev
    Next
    INDEX
    Explanations

    utility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    }/>
    2.83
     majesty
    2.53
     rodeo
    2.52
    }`,
    2.52
    诵
    2.49
     arbitration
    2.49
     foremost
    2.47
    𝐯
    2.45
     başta
    2.41
    pictures
    2.36
    POSITIVE LOGITS
     ích
    2.28
    नाइटेड
    2.10
     heap
    2.07
    ْم
    1.96
     glowing
    1.95
    фика
    1.95
    
    1.94
    ган
    1.93
    illumin
    1.92
    denly
    1.92
    Activations Density 0.096%

    No Known Activations