© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13104
    Prev
    Next
    INDEX
    Explanations

    words related to regulations, organization, studies, or legalities and their outcomes, often appearing among plural terms or lists

    oai_token-act-pair · gemini-2.0-flash

    specific details

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    MessageTagHelper
    -0.72
    posedge
    -0.70
    ंदीखरीदारी
    -0.70
    참고
    -0.67
    complexContent
    -0.66
    enterOuterAlt
    -0.65
    aarrggbb
    -0.65
     precisamente
    -0.65
    rivit
    -0.62
    DoubleQuotes
    -0.61
    POSITIVE LOGITS
     either
    0.62
    Either
    0.59
    either
    0.54
     orice
    0.51
     Either
    0.49
     companies
    0.48
    requireNonNull
    0.47
     apapun
    0.44
     चीज़ों
    0.44
     entweder
    0.43
    Activations Density 4.984%

    No Known Activations