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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3600
    Prev
    Next
    INDEX
    Explanations

    not that

    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
    ்ட்
    1.21
    ాన్
    0.97
    стю
    0.90
     }>;
    0.87
     etiam
    0.87
    сист
    0.87
     averaged
    0.86
     উপায়
    0.85
    grey
    0.85
    ਠ
    0.85
    POSITIVE LOGITS
    it
    0.96
     demás
    0.91
    𝑒
    0.90
     tecnológicos
    0.86
     conquist
    0.85
     diri
    0.85
    𝒾
    0.85
    𝐼
    0.84
     কাশি
    0.83
     motivating
    0.83
    Activations Density 0.011%

    No Known Activations