© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6643
    Prev
    Next
    INDEX
    Explanations

    the word "sector" or the name "Max"

    oai_token-act-pair · gemini-2.0-flash

    economics sector

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    coper
    -0.67
    ponte
    -0.61
     dest
    -0.61
    EDES
    -0.60
    paux
    -0.59
    mogorov
    -0.57
     Max
    -0.57
     cont
    -0.57
    #+#
    -0.56
    pylab
    -0.56
    POSITIVE LOGITS
     auroit
    1.03
     feroit
    1.01
     aveug
    0.96
     giustizia
    0.95
     déchir
    0.90
     pouvoit
    0.88
     spesa
    0.86
     avoient
    0.82
     étoit
    0.82
     preghiera
    0.82
    Activations Density 1.597%

    No Known Activations