© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 123
    Prev
    Next
    INDEX
    Explanations

    language used in corporate mission statements

    oai_token-act-pair · gemini-2.0-flash

    healthy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     AssemblyCulture
    -0.49
    ScopeManager
    -0.43
     invokingState
    -0.42
     bestand
    -0.41
     Pronto
    -0.41
    цей
    -0.41
     sev
    -0.41
    <eos>
    -0.40
     Woodlands
    -0.40
     unrelated
    -0.40
    POSITIVE LOGITS
    AndEndTag
    0.75
     препратки
    0.70
     CreateTagHelper
    0.70
     تانيه
    0.68
    VIAF
    0.67
    enderror
    0.66
    ViewImports
    0.63
    OGND
    0.61
     Administrativna
    0.59
    cloudflare
    0.57
    Activations Density 0.740%

    No Known Activations