© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 496
    Prev
    Next
    INDEX
    Explanations

    phrases related to business

    oai_token-act-pair · gemini-2.0-flash

    Business expansion; Peter

    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
     <<=
    -0.52
     sogno
    -0.52
    isma
    -0.52
     lapel
    -0.46
    rasında
    -0.46
    utched
    -0.46
     modality
    -0.45
     ettiği
    -0.45
    empereur
    -0.44
     linie
    -0.44
    POSITIVE LOGITS
    ArrowToggle
    0.71
     onOptions
    0.60
    contentLoaded
    0.59
    NameInMap
    0.58
     SwitchCompat
    0.57
     يتيمه
    0.56
     /\.(
    0.56
    multer
    0.53
     CGSize
    0.53
    hydrat
    0.53
    Activations Density 31.143%

    No Known Activations