© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11516
    Prev
    Next
    INDEX
    Explanations

    tokens ending in the letters "req"

    oai_token-act-pair · gemini-2.0-flash

    req

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    req
    -1.21
     req
    -1.13
    UrlResolution
    -0.74
     opérateur
    -0.72
     Req
    -0.68
    Req
    -0.68
    География
    -0.66
     nahilalakip
    -0.65
     Call
    -0.63
    REQ
    -0.62
    POSITIVE LOGITS
    assert
    0.57
     grammi
    0.56
    édrale
    0.53
     jScrollPane
    0.52
     Weak
    0.49
    weakSelf
    0.49
    깥
    0.48
     weak
    0.48
    Factories
    0.47
     WHETHER
    0.47
    Activations Density 0.083%

    No Known Activations