© 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-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9430
    Prev
    Next
    INDEX
    Explanations

    a mix of words with the letters UT, sports figures' names, and some foreign words

    oai_token-act-pair · gemini-2.0-flash

    ut

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.92
    ut
    -0.91
     myſelf
    -0.81
     Jefus
    -0.80
    ſelves
    -0.79
     GenerationType
    -0.78
     Monfieur
    -0.77
     itſelf
    -0.76
    ſelf
    -0.75
     Theſe
    -0.75
    POSITIVE LOGITS
     Post
    0.50
     post
    0.50
    หลัง
    0.48
    ///</
    0.48
     Real
    0.46
    tuan
    0.45
    webElement
    0.44
     poste
    0.44
    пут
    0.44
     کش
    0.43
    Activations Density 5.953%

    No Known Activations