© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8000
    Prev
    Next
    INDEX
    Explanations

    mentions of a "SANG" and nearby words, in the context of residential development

    oai_token-act-pair · gemini-2.0-flash

    obscure language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     <<<<<<<<<<<<<<
    -0.58
    ⓧ
    -0.56
     SEDS
    -0.48
    nościo
    -0.48
    ötä
    -0.48
     Smarty
    -0.46
    ressee
    -0.45
    cided
    -0.45
    intios
    -0.45
    ItemLayout
    -0.44
    POSITIVE LOGITS
    astify
    0.71
    tvguidetime
    0.63
    例文帳に追加
    0.57
     autorytatywna
    0.56
    RegressionTest
    0.54
    BASEPATH
    0.53
    цездатний
    0.52
    protoc
    0.52
     Mifflin
    0.52
    |}{
    0.51
    Activations Density 1.551%

    No Known Activations