© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3138
    Prev
    Next
    INDEX
    Explanations

    words in a mix of languages, including Malay, and some proper nouns.

    oai_token-act-pair · gemini-2.0-flash

    ambil

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    
    -0.75
    BagLayout
    -0.71
    Datuak
    -0.69
    __(/*!
    -0.66
     PopupWindow
    -0.64
    Portály
    -0.62
     محفوظة
    -0.60
     Sew
    -0.60
    tagext
    -0.60
    XmlAccessType
    -0.59
    POSITIVE LOGITS
    verwijspagina
    0.51
    GEBURTSDATUM
    0.42
     تانيه
    0.41
     guardia
    0.41
    tuan
    0.40
    MessageTagHelper
    0.40
    áll
    0.37
    ietal
    0.37
     Wikimedijinoj
    0.37
     "",
    
    0.36
    Activations Density 0.377%

    No Known Activations