© 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. 409
    Prev
    Next
    INDEX
    Explanations

    phrases indicating surprise, opinions, or disbelief.

    oai_token-act-pair · gemini-2.0-flash

    colloquial language

    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
     EconPapers
    -0.94
    LookAnd
    -0.92
    esgue
    -0.85
     дописавши
    -0.84
    DockStyle
    -0.84
     '\\;'
    -0.81
    ----</
    -0.77
     HasFactory
    -0.77
    TypedDataSet
    -0.76
    MigrationBuilder
    -0.76
    POSITIVE LOGITS
     pinball
    0.39
     cominci
    0.38
     venido
    0.38
    czaj
    0.37
    出版社
    0.37
     mutu
    0.36
    <strong>
    0.35
     prostu
    0.35
    relativeTime
    0.35
     rând
    0.35
    Activations Density 3.747%

    No Known Activations