© 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. 10091
    Prev
    Next
    INDEX
    Explanations

    phrases related to maintaining or managing something

    oai_token-act-pair · gemini-2.0-flash

    keep

    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
     Keep
    -0.93
     keep
    -0.92
    keep
    -0.88
     kept
    -0.86
    Keep
    -0.85
     KEEP
    -0.82
     Keeping
    -0.82
    KEEP
    -0.82
    Keeping
    -0.82
    kept
    -0.80
    POSITIVE LOGITS
     ujednoznacz
    0.68
    جغرافيا
    0.57
     ErrInvalid
    0.57
     predeceased
    0.56
     שוליים
    0.56
    Réalisation
    0.54
     undo
    0.54
    исленность
    0.53
     Hän
    0.53
    
    0.52
    Activations Density 10.566%

    No Known Activations