Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 4459
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    ет
    2.50
    و
    2.47
    ы
    2.19
    ا
    2.15
    ly
    1.85
    ్
    1.84
     inex
    1.81
    ாக
    1.78
    р
    1.75
    ভাবে
    1.73
    POSITIVE LOGITS
    𝗻
    1.98
    ровать
    1.84
    ﻥ
    1.78
    ので
    1.74
    そのため
    1.73
    िक्रमा
    1.72
    ᷄
    1.69
    আ
    1.68
    ただし
    1.63
     类型
    1.62
    Activations Density 0.092%

    No Known Activations