© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12075
    Prev
    Next
    INDEX
    Explanations

    This neuron appears to be identifying noun phrases related to a variety of topics, including genetics, history, medicine, law, and celebrity gossip

    oai_token-act-pair · gemini-2.0-flash

    genetics research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    <bos>
    -0.54
    StoreMessageInfo
    -0.54
     externi
    -0.50
     Italijani
    -0.50
     "..\..\..\
    -0.49
    السكان
    -0.48
     '\\;'
    -0.47
    IndentedString
    -0.47
     nahilalakip
    -0.47
    EndGlobalSection
    -0.47
    POSITIVE LOGITS
    OOTDTY
    0.82
     Efq
    0.75
     تضيفلها
    0.66
    findpost
    0.63
     purpoſe
    0.62
     Majefty
    0.60
    ESTAMP
    0.59
     fevere
    0.59
    rrggbb
    0.59
     Chriftian
    0.58
    Activations Density 12.889%

    No Known Activations