© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12091
    Prev
    Next
    INDEX
    Explanations

    dates and measurements

    oai_token-act-pair · gemini-2.0-flash

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    PreferredItem
    -0.76
     ProtoMessage
    -0.68
    CppMethod
    -0.63
    发表于
    -0.54
    脚注の使い方
    -0.54
    
    -0.54
    inflater
    -0.52
     autorytatywna
    -0.50
    omitempty
    -0.50
    ZEL
    -0.49
    POSITIVE LOGITS
     operacional
    0.64
    machus
    0.60
    epiece
    0.58
     Tripod
    0.54
    Xamarin
    0.53
     beslu
    0.53
     recevrez
    0.53
     وعلى
    0.52
    irical
    0.52
     оригіналу
    0.52
    Activations Density 1.252%

    No Known Activations