© 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. 11171
    Prev
    Next
    INDEX
    Explanations

    significant historical events and figures

    oai_token-act-pair · gemini-2.0-flash

    Important events

    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
     autorytatywna
    -0.59
    cyklopedia
    -0.57
    onViewCreated
    -0.55
    zeera
    -0.51
    thodoxy
    -0.50
     }}"></
    -0.50
    Abitanti
    -0.48
    thaf
    -0.48
    '][$
    -0.48
    CopyWith
    -0.48
    POSITIVE LOGITS
    SceneManagement
    0.72
    MediaStore
    0.65
    
    0.57
    MENAFN
    0.56
    numberOfLines
    0.55
    niejsza
    0.52
     unknownFields
    0.51
     celebrated
    0.50
    beros
    0.50
     Truppen
    0.49
    Activations Density 0.951%

    No Known Activations