© 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. 6044
    Prev
    Next
    INDEX
    Explanations

    scientific and technical vocabulary

    oai_token-act-pair · gemini-2.0-flash

    Scientific research

    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
    rungsseite
    -0.73
    Personendaten
    -0.64
     intptr
    -0.60
    ValueStyle
    -0.59
     GeoNames
    -0.57
    TabIndex
    -0.57
     AssemblyCulture
    -0.56
    enumii
    -0.54
     Dome
    -0.52
    Diwedd
    -0.52
    POSITIVE LOGITS
     jellemző
    0.52
    chnung
    0.50
    tolsó
    0.48
     slippage
    0.48
    MigrationBuilder
    0.48
    droje
    0.47
    Risultati
    0.47
    elenco
    0.46
     giapp
    0.46
     setName
    0.46
    Activations Density 7.552%

    No Known Activations