Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14617
    Prev
    Next
    INDEX
    Explanations

    usernames or acronyms mixed with numbers

    oai_token-act-pair · gemini-2.0-flash

    conversing with Mblanc46

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     M
    -0.61
     Le
    -0.57
     Ter
    -0.57
     Al
    -0.57
     Ma
    -0.56
     Jan
    -0.56
     Sta
    -0.54
     Dam
    -0.54
     V
    -0.54
     A
    -0.54
    POSITIVE LOGITS
     Efq
    1.17
    expandindo
    1.09
     Monfieur
    1.07
     Majefty
    1.06
     ―――――
    1.04
     doubtnut
    1.02
     photolibrary
    1.00
    ſelf
    0.98
     Shakspeare
    0.98
     Cæsar
    0.96
    Activations Density 2.166%

    No Known Activations