© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 962
    Prev
    Next
    INDEX
    Explanations

    phrases related to indecision and putting things off

    oai_token-act-pair · gemini-2.0-flash

    pausing or delaying

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    WebElementEntity
    -0.91
     defaultstate
    -0.75
     InputDecoration
    -0.72
     useRouter
    -0.72
    webElementGuid
    -0.71
     betweenstory
    -0.69
    mapStateToProps
    -0.67
    |}{\
    -0.64
    ]")]
    -0.64
    ksikon
    -0.63
    POSITIVE LOGITS
     postponed
    0.79
     postpone
    0.77
     defer
    0.74
     delay
    0.70
     postpon
    0.69
     postponement
    0.68
     temporarily
    0.65
     pause
    0.64
     wait
    0.63
     delayed
    0.63
    Activations Density 0.995%

    No Known Activations