© 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. 3692
    Prev
    Next
    INDEX
    Explanations

    words related to restricting and diminishing

    oai_token-act-pair · gemini-2.0-flash

    lighten or tighten

    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
     GenerationType
    -0.95
    BeginContext
    -0.88
    AccessorTable
    -0.87
    parsedMessage
    -0.85
    tagHelperRunner
    -0.85
     defaultstate
    -0.85
     MonoBehaviour
    -0.84
    iastes
    -0.79
    WaitGroup
    -0.78
     متعلقه
    -0.78
    POSITIVE LOGITS
     up
    0.79
     terms
    0.59
     parameter
    0.58
     line
    0.57
     profile
    0.57
     way
    0.56
    Up
    0.54
    <bos>
    0.54
     time
    0.53
    ness
    0.53
    Activations Density 3.353%

    No Known Activations