© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12365
    Prev
    Next
    INDEX
    Explanations

    occurrences of numbers, including those written as words and those involved in hyphenated phrases

    oai_token-act-pair · gemini-2.0-flash

    Connects words in a sentence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    MigrationBuilder
    -0.82
    K
    -0.82
    ValueStyle
    -0.79
    G
    -0.78
    T
    -0.78
     K
    -0.75
    IUrlHelper
    -0.75
    ıyordu
    -0.74
    adze
    -0.74
    Time
    -0.74
    POSITIVE LOGITS
    <bos>
    0.51
    FTFY
    0.41
    Viited
    0.36
    存于互联网档案馆
    0.35
    ,‎
    0.34
    はじめに
    0.32
       
    0.31
    NUMX
    0.29
    Conexao
    0.27
     Vedi
    0.27
    Activations Density 13.116%

    No Known Activations