© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2063
    Prev
    Next
    INDEX
    Explanations

    phrases regarding the concept of justice, benefit, or convenience.

    oai_token-act-pair · gemini-2.0-flash

    legal and political text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    httphttps
    -0.63
    WithIOException
    -0.63
    ]")]
    -0.59
    itness
    -0.56
    thâu
    -0.54
     Wiktionnaire
    -0.54
    ArgsConstructor
    -0.54
    akuza
    -0.54
    AddTagHelper
    -0.53
    Lähteet
    -0.52
    POSITIVE LOGITS
     Ngb
    0.49
    invokeLater
    0.47
    TagHelpers
    0.46
    Accurate
    0.46
    données
    0.45
     Theſe
    0.44
    SetOutput
    0.43
    ฐ
    0.43
    lished
    0.43
     drept
    0.43
    Activations Density 1.870%

    No Known Activations