© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8671
    Prev
    Next
    INDEX
    Explanations

    mentions of oil and gas companies and their operation areas.

    oai_token-act-pair · gemini-2.0-flash

    oil

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     चीज़ों
    -0.84
     numberWith
    -0.74
     Chriftian
    -0.69
     cherchés
    -0.67
    CloseOperation
    -0.66
    ]")]
    -0.66
    cookieParser
    -0.65
    الحياه
    -0.65
    makeConstraints
    -0.64
     consultato
    -0.63
    POSITIVE LOGITS
    field
    0.56
    fields
    0.53
    filed
    0.46
    fied
    0.42
    well
    0.41
    fiel
    0.41
    FIELD
    0.40
    Ep
    0.40
    ätter
    0.40
     fields
    0.40
    Activations Density 2.773%

    No Known Activations