© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4963
    Prev
    Next
    INDEX
    Explanations

    section headers in scientific articles

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    (
    -0.71
    :
    -0.59
    ,
    -0.58
     оригіналу
    -0.56
    -
    -0.56
     protoimpl
    -0.51
    parsedMessage
    -0.50
    
    -0.49
    $
    -0.47
     pat
    -0.46
    POSITIVE LOGITS
     TÉCNICA
    0.62
     estimés
    0.60
     Técnica
    0.59
     habet
    0.59
     Nami
    0.57
    RectangleBorder
    0.55
     noDo
    0.54
     Italijani
    0.53
     varandra
    0.53
     vectorielles
    0.53
    Activations Density 14.194%

    No Known Activations