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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14499
    Prev
    Next
    INDEX
    Explanations

    titles for articles about business, real estate, or marketing

    oai_token-act-pair · gemini-2.0-flash

    informational texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     useRouter
    -0.59
     greateſt
    -0.56
     beſt
    -0.53
     durs
    -0.53
     useAuth
    -0.52
     Calvo
    -0.52
     IService
    -0.50
     habet
    -0.50
     bilin
    -0.50
     ſte
    -0.50
    POSITIVE LOGITS
     Of
    1.40
     And
    1.23
     To
    1.21
     For
    1.14
     On
    1.02
     In
    0.91
    Of
    0.90
     Or
    0.87
     From
    0.85
     At
    0.84
    Activations Density 3.200%

    No Known Activations