© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10468
    Prev
    Next
    INDEX
    Explanations

    words associated with websites as well as social activity and collaboration

    oai_token-act-pair · gemini-2.0-flash

    online content and accessibility

    np_token-act-pair-logits · gpt-4o-mini

    website

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     online
    -2.36
    Online
    -2.06
     Online
    -2.06
    online
    -2.03
     ONLINE
    -1.97
    ONLINE
    -1.77
     internet
    -1.74
     Internet
    -1.70
    Internet
    -1.66
    internet
    -1.63
    POSITIVE LOGITS
    findpost
    0.61
    uxxxx
    0.48
     embedding
    0.48
     uLocal
    0.47
    ufige
    0.45
    enumii
    0.44
    ########.
    0.44
     embed
    0.44
    oring
    0.43
     fresh
    0.43
    Activations Density 4.231%

    No Known Activations