© 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. 12010
    Prev
    Next
    INDEX
    Explanations

    references to laws, acts, sections, or government documents

    oai_token-act-pair · gemini-2.0-flash

    legal documents and proceedings

    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
     nonatomic
    -0.54
    allon
    -0.54
    dike
    -0.51
    nicas
    -0.50
    anteed
    -0.49
    orias
    -0.48
    nourished
    -0.47
    createCanvas
    -0.47
    ghed
    -0.46
     LUMP
    -0.46
    POSITIVE LOGITS
    AccessorTable
    0.80
    !*\
    0.68
    featureID
    0.64
    URLException
    0.62
    Unmarshaller
    0.58
    :✨
    0.56
     spéciales
    0.56
    gameserver
    0.54
    keyColumn
    0.52
    WriteBarrier
    0.52
    Activations Density 6.903%

    No Known Activations