© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8311
    Prev
    Next
    INDEX
    Explanations

    academic papers and formal legal documents, especially references to sections/appendices and the word "following"

    oai_token-act-pair · gemini-2.0-flash

    legal and code

    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
     Telephone
    -0.69
     References
    -0.67
     Correspondence
    -0.66
     autorytatywna
    -0.63
     Página
    -0.62
    liothèque
    -0.61
     صوتيه
    -0.60
     Transcript
    -0.59
     Three
    -0.59
     Two
    -0.59
    POSITIVE LOGITS
    Best
    0.59
    Produce
    0.57
    Helps
    0.57
    Traits
    0.54
    Own
    0.53
     Best
    0.53
    Provide
    0.53
     Helps
    0.53
    Utili
    0.52
     Estab
    0.52
    Activations Density 16.234%

    No Known Activations