© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2609
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to focus or drawing interest or historical studies

    oai_token-act-pair · gemini-2.0-flash

    attention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     attention
    -2.83
     Attention
    -2.47
    attention
    -2.31
    Attention
    -2.30
     ATTENTION
    -1.98
     attentions
    -1.72
     Aufmerksamkeit
    -1.66
     внимание
    -1.58
     aandacht
    -1.58
    attenzione
    -1.55
    POSITIVE LOGITS
     decking
    0.60
    ReusableCell
    0.58
    tonsoft
    0.58
    RTLR
    0.56
    IsMutable
    0.55
    EndInit
    0.54
    oldown
    0.54
     IMPLIED
    0.54
     Maori
    0.53
    IInterface
    0.51
    Activations Density 9.507%

    No Known Activations