© 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. 15225
    Prev
    Next
    INDEX
    Explanations

    code snippets related to testing, JSON data or network protocols, with emphasis on identifying errors, connections, and function execution

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
    AddTagHelper
    -1.07
     esternos
    -1.05
    tvguidetime
    -1.02
    GEBURTSDATUM
    -1.02
    CloseOperation
    -1.02
     resourceCulture
    -1.02
     initComponents
    -1.00
    PreferredItem
    -1.00
     CreateTagHelper
    -0.98
    Manbalar
    -0.98
    POSITIVE LOGITS
    !
    0.56
    <eos>
    0.53
    .
    0.52
    !!
    0.46
    :(
    0.45
    :
    0.45
    !,
    0.45
    !(
    0.45
    ?
    0.44
     ocasião
    0.44
    Activations Density 8.527%

    No Known Activations