© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10495
    Prev
    Next
    INDEX
    Explanations

    code snippets, Portuguese words, and the word "jogador."

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Життєпис
    -0.56
     مواليد
    -0.56
     distanciation
    -0.52
     Uribe
    -0.51
     Clapton
    -0.51
     Barrera
    -0.50
    enosis
    -0.48
     Shakira
    -0.47
     MonoBehaviour
    -0.46
    FieldOffset
    -0.46
    POSITIVE LOGITS
    expandindo
    0.73
    AsUp
    0.61
    RegressionTest
    0.61
    nós
    0.61
    újo
    0.59
    脚注の使い方
    0.58
    outros
    0.58
    出版年
    0.58
    protetor
    0.57
    são
    0.56
    Activations Density 18.672%

    No Known Activations