© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 5133
    Prev
    Next
    INDEX
    Explanations

    academic references with authors and titles

    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
    م
    1.79
     troubled
    1.32
     त्यस
    1.26
    teen
    1.26
    үр
    1.24
    aient
    1.21
     sophisticated
    1.21
    돔
    1.16
    ॉर्म
    1.14
     Eğer
    1.14
    POSITIVE LOGITS
    aching
    1.27
    此之外
    1.22
    ached
    1.20
     След
    1.17
    桃
    1.15
    #######
    1.12
    izing
    1.12
    ளிய
    1.10
     मिलाकर
    1.09
    ला
    1.09
    Activations Density 0.003%

    No Known Activations