© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15221
    Prev
    Next
    INDEX
    Explanations

    code snippets/examples of C# code

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ècie
    -0.61
     Vikipedi
    -0.61
    ]=>
    -0.59
    rungsseite
    -0.59
    ագրություններ
    -0.53
    prnewswire
    -0.51
    Hozzáférés
    -0.51
     Wart
    -0.51
     Cale
    -0.51
    ərbaycan
    -0.49
    POSITIVE LOGITS
     Normdatei
    0.58
    /*-
    0.54
     mesta
    0.49
    featureID
    0.49
     me
    0.48
    Me
    0.48
     marea
    0.47
    govina
    0.46
     torchvision
    0.46
    śmie
    0.46
    Activations Density 1.276%

    No Known Activations