© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9321
    Prev
    Next
    INDEX
    Explanations

    varied phrases that contain words like "cost", "matter", "know", "goodness", "easy", or words indicating amount

    oai_token-act-pair · gemini-2.0-flash

    sacrifice, cost

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    expandindo
    -0.66
     متعلقه
    -0.60
    Източници
    -0.59
    󠁢
    -0.55
     مشين
    -0.55
     autorytatywna
    -0.52
    MessageTagHelper
    -0.52
    Hauptartikel
    -0.52
     betweenstory
    -0.52
    Vidite
    -0.52
    POSITIVE LOGITS
     sacrifice
    0.81
     sacrifices
    0.78
     inconvenience
    0.76
    COST
    0.69
     sacrificio
    0.69
    pain
    0.66
     risk
    0.65
     cost
    0.64
     sacrificed
    0.64
     risks
    0.64
    Activations Density 1.952%

    No Known Activations