© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3460
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to medieval European aristocracy and governance.

    oai_token-act-pair · gemini-2.0-flash

    European history and governance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     <<<<<<<<<<<<<<
    -0.60
    queryInterface
    -0.59
     jLabel
    -0.59
     ModelExpression
    -0.54
     autorytatywna
    -0.53
    Rhestr
    -0.50
    Personensuche
    -0.50
     Italijani
    -0.50
    ReusableCell
    -0.50
    ViewFeatures
    -0.48
    POSITIVE LOGITS
    TextHelper
    0.54
    ulantes
    0.52
     trusts
    0.50
    UnknownFieldSet
    0.47
    herzog
    0.47
    mtr
    0.47
    نر
    0.47
     fyr
    0.46
     Hauptmann
    0.46
     Trusts
    0.45
    Activations Density 4.977%

    No Known Activations