© 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. 6203
    Prev
    Next
    INDEX
    Explanations

    words related to web design and search engine optimization

    oai_token-act-pair · gemini-2.0-flash

    site

    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
     site
    -2.61
     Site
    -2.38
    site
    -2.36
    Site
    -2.28
     sites
    -2.28
     Sites
    -2.16
     SITE
    -2.14
    SITE
    -1.98
    Sites
    -1.91
    sites
    -1.88
    POSITIVE LOGITS
    writeFieldEnd
    0.72
     onOptions
    0.68
    Personendaten
    0.65
    utilisons
    0.64
    ]='\
    0.63
    enderror
    0.62
     invokingState
    0.57
    ulgação
    0.57
    setVerticalGroup
    0.54
    providedIn
    0.54
    Activations Density 4.171%

    No Known Activations