© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11915
    Prev
    Next
    INDEX
    Explanations

    In this highly technical document, the neuron seems to identify titles of scientific publications alongside related terms.

    oai_token-act-pair · gemini-2.0-flash

    Rev, transactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     كمان
    -0.47
     végét
    -0.43
    URL
    -0.41
    far
    -0.40
     near
    -0.39
    out
    -0.39
     chimiques
    -0.39
    near
    -0.37
    zwischen
    -0.36
    ngOnInit
    -0.36
    POSITIVE LOGITS
    LookAnd
    1.28
    ReusableCell
    1.11
    SequentialGroup
    1.03
    WebElementEntity
    1.03
     typelib
    0.98
    protoimpl
    0.97
    featureID
    0.97
     betweenstory
    0.96
    bootstrapcdn
    0.96
    تقاوى
    0.96
    Activations Density 2.088%

    No Known Activations