© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5646
    Prev
    Next
    INDEX
    Explanations

    code blocks

    oai_token-act-pair · gemini-2.0-flash

    technical terms and code elements

    np_token-act-pair-logits · gpt-4o-mini

    Code-related names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    nestjs
    -0.53
    <bos>
    -0.52
     qua
    -0.43
    ups
    -0.42
    Viitteet
    -0.39
    ্ব
    -0.38
    出版年
    -0.38
    IsOptional
    -0.38
    ista
    -0.38
     مق
    -0.37
    POSITIVE LOGITS
    tvguidetime
    0.94
    MessageTagHelper
    0.79
    protoimpl
    0.66
    
    0.65
     ſever
    0.64
    SourceChecksum
    0.63
     Roskov
    0.62
     InputDecoration
    0.62
     EconPapers
    0.60
     AssemblyProduct
    0.59
    Activations Density 0.639%

    No Known Activations