© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4071
    Prev
    Next
    INDEX
    Explanations

    intensifiers and qualifiers like "nearly as", "matter how", "bit as", and "perhaps".

    oai_token-act-pair · gemini-2.0-flash

    Comparisons and quantities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     meglio
    -0.52
     ANCHE
    -0.51
     quelli
    -0.50
    SuppressMessage
    -0.45
    页面存档备份
    -0.45
    以外は
    -0.45
    ODB
    -0.43
    webElementXpaths
    -0.43
    OutOfBounds
    -0.43
     EconPapers
    -0.42
    POSITIVE LOGITS
     such
    1.16
     Such
    1.01
    Such
    0.96
     SUCH
    0.84
    such
    0.84
    AnimationsModule
    0.76
     такой
    0.74
     Такие
    0.73
     så
    0.73
     Chwiliwch
    0.72
    Activations Density 0.668%

    No Known Activations