© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3202
    Prev
    Next
    INDEX
    Explanations

    capitalized words and software related terminology

    oai_token-act-pair · gemini-2.0-flash

    companies

    np_max-act-logits · gemini-2.0-flash

    say "company suffixes"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     services
    -0.59
    LookAnd
    -0.57
     nonatomic
    -0.52
    WebElementEntity
    -0.50
     transport
    -0.49
     dikt
    -0.49
     transportation
    -0.49
     technology
    -0.48
    évaluateur
    -0.48
    :✨
    -0.48
    POSITIVE LOGITS
     Plural
    0.48
     himo
    0.48
     arşivlendi
    0.46
    IntoConstraints
    0.46
    LY
    0.45
    jooq
    0.45
    ImageContext
    0.44
    isome
    0.44
    classnames
    0.44
    IRM
    0.43
    Activations Density 10.121%

    No Known Activations