© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9619
    Prev
    Next
    INDEX
    Explanations

    the word "work"

    oai_token-act-pair · gemini-2.0-flash

    work

    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
    AddTagHelper
    -0.99
    +#+#
    -0.94
     autorytatywna
    -0.92
     kasarigan
    -0.91
    ValueStyle
    -0.90
    Tikang
    -0.87
    <bos>
    -0.86
    CloseOperation
    -0.85
    TestingModule
    -0.84
     '\\;'
    -0.84
    POSITIVE LOGITS
    old
    0.54
    !
    0.54
    ↵↵
    0.49
     برف
    0.46
    a
    0.45
      
    0.44
    \\
    0.43
     (
    0.42
    or
    0.40
     realising
    0.40
    Activations Density 0.110%

    No Known Activations