© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15400
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings in Penobscot County

    oai_token-act-pair · gemini-2.0-flash

    obs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    meneu
    -0.49
     unw
    -0.49
    hlor
    -0.49
    ulents
    -0.48
     wur
    -0.47
    ollectionView
    -0.46
     Wali
    -0.45
    undial
    -0.45
     Sahib
    -0.44
     eerst
    -0.43
    POSITIVE LOGITS
    <bos>
    0.85
    reactstrap
    0.79
    脚注の使い方
    0.75
    Datuak
    0.64
    Lähteet
    0.62
     nahilalakip
    0.59
    
    0.59
    BeginInit
    0.58
    Hozzáférés
    0.57
    AddTagHelper
    0.54
    Activations Density 2.392%

    No Known Activations