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. 4100
    Prev
    Next
    INDEX
    Explanations

    Chrome browser

    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_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
    ্ঠ
    1.69
    ㅜ
    1.61
     humanities
    1.60
    ்த்து
    1.57
    처
    1.57
     ease
    1.56
    kaj
    1.56
     сам
    1.56
    u
    1.54
    கள்
    1.53
    POSITIVE LOGITS
     хвата
    1.55
     døde
    1.51
     navigateur
    1.48
     брау
    1.46
    корд
    1.44
     خدا
    1.44
    𝑟
    1.43
    と思います
    1.43
    𝑑
    1.42
    лиз
    1.40
    Activations Density 0.025%

    No Known Activations