© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13333
    Prev
    Next
    INDEX
    Explanations

    words related to academic or research reports

    oai_token-act-pair · gemini-2.0-flash

    validating facts and information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    intios
    -0.85
    DockStyle
    -0.85
    SharedDtor
    -0.84
     Савезне
    -0.83
     AssemblyCulture
    -0.82
     Bourgoin
    -0.81
    ьаж
    -0.80
     виправивши
    -0.77
    ագրություններ
    -0.75
     Roskov
    -0.74
    POSITIVE LOGITS
    cad
    0.52
    ing
    0.49
    bindParam
    0.49
    PropertyChanged
    0.47
    кра
    0.47
    不可
    0.47
    ята
    0.47
     esti
    0.46
    ộc
    0.46
    ungk
    0.45
    Activations Density 0.802%

    No Known Activations