© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9558
    Prev
    Next
    INDEX
    Explanations

    mentions of asking questions or making requests

    oai_token-act-pair · gemini-2.0-flash

    asking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     saying
    -1.66
     alleging
    -1.64
    saying
    -1.59
     stating
    -1.54
     thanking
    -1.52
     noting
    -1.51
     diciendo
    -1.47
     arguing
    -1.47
     mentioning
    -1.46
     insisting
    -1.45
    POSITIVE LOGITS
    ning
    0.71
     call
    0.66
    NING
    0.64
    ting
    0.62
    idin
    0.61
    ZING
    0.61
    ping
    0.60
     present
    0.60
    катери
    0.60
     report
    0.59
    Activations Density 4.452%

    No Known Activations