© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11137
    Prev
    Next
    INDEX
    Explanations

    words related to running tasks or searches

    oai_token-act-pair · gemini-2.0-flash

    run

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     run
    -1.33
     Running
    -1.15
     runs
    -1.13
     running
    -1.13
    run
    -1.06
     Run
    -1.05
    Running
    -1.05
     Runs
    -1.04
    Run
    -1.01
     RUN
    -1.01
    POSITIVE LOGITS
    ⓧ
    0.51
    enterOuterAlt
    0.51
     שוליים
    0.49
    comy
    0.47
    isMethod
    0.45
    remo
    0.45
     cách
    0.44
    лько
    0.44
     la
    0.43
    書き
    0.43
    Activations Density 22.884%

    No Known Activations