© 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. 207
    Prev
    Next
    INDEX
    Explanations

    words from technical and academic writing about computer science and mathematics

    oai_token-act-pair · gemini-2.0-flash

    Technical/programming context

    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
    <bos>
    -0.56
    protoimpl
    -0.54
    ]").
    -0.51
    wdriver
    -0.51
    NSYLVANIA
    -0.49
     Italijanski
    -0.49
     تانيه
    -0.49
    okovic
    -0.48
    astéro
    -0.48
    RTLD
    -0.47
    POSITIVE LOGITS
    mybatisplus
    0.63
     resourceCulture
    0.60
    脚注の使い方
    0.56
    AutoScaleMode
    0.52
    truncate
    0.51
    出版年
    0.51
     Stolz
    0.50
    Sortie
    0.50
    Slf
    0.50
     ostavi
    0.50
    Activations Density 10.581%

    No Known Activations