© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11297
    Prev
    Next
    INDEX
    Explanations

    the word "commitment"

    oai_token-act-pair · gemini-2.0-flash

    commitment

    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
     Leader
    -0.62
    ”
    -0.56
    I
    -0.56
     mandatory
    -0.55
     commitment
    -0.55
     tr
    -0.54
     commitments
    -0.53
    Leader
    -0.53
     mandated
    -0.52
     Mandatory
    -0.51
    POSITIVE LOGITS
    EndProject
    0.77
    IonicModule
    0.76
    expandindo
    0.76
    TagMode
    0.75
    ValueStyle
    0.73
     Efq
    0.72
     ―――――
    0.71
     виправивши
    0.71
    HtmlAttribute
    0.71
     raiſ
    0.70
    Activations Density 1.605%

    No Known Activations