© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13186
    Prev
    Next
    INDEX
    Explanations

    mentions of water, chemicals, polymers and scientific experiments

    oai_token-act-pair · gemini-2.0-flash

    technical or programming-related terms

    np_token-act-pair-logits · gpt-4o-mini

    chemical reactions and polymers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Datuak
    -0.78
    DllImport
    -0.65
    Transkript
    -0.60
    IBOutlet
    -0.58
     <<<<<<<<<<<<<<
    -0.57
    clearInterval
    -0.57
    存于互联网档案馆
    -0.56
     smtplib
    -0.53
    onViewCreated
    -0.53
     '\\;'
    -0.52
    POSITIVE LOGITS
    CodeAttribute
    0.55
    AppCompat
    0.51
    PageModule
    0.49
    ReusableCell
    0.48
    ➞
    0.48
    huriyet
    0.45
    taur
    0.45
    Scalars
    0.45
    grà
    0.45
    ScopeManager
    0.44
    Activations Density 2.212%

    No Known Activations