© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10910
    Prev
    Next
    INDEX
    Explanations

    words related to the extraction of nickel from the earth

    oai_token-act-pair · gemini-2.0-flash

    Mining and ores

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     estekak
    -0.93
    BagConstraints
    -0.82
     الحره
    -0.77
    parsedMessage
    -0.75
     cherchés
    -0.74
    migrationBuilder
    -0.73
     فريبيس
    -0.73
    WithIOException
    -0.73
    Personensuche
    -0.72
    BufferException
    -0.72
    POSITIVE LOGITS
    perma
    0.41
    submenu
    0.41
    sub
    0.39
     l
    0.39
     sub
    0.39
     L
    0.38
    mig
    0.38
    Race
    0.38
    ś
    0.37
     migrantes
    0.37
    Activations Density 0.871%

    No Known Activations