© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12085
    Prev
    Next
    INDEX
    Explanations

    text in another language, especially Greek

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    MigrationBuilder
    -1.05
     resourceCulture
    -1.05
    AccessorTable
    -1.02
     BrowserModule
    -1.01
    endphp
    -1.00
     Мексичка
    -1.00
     NgModule
    -0.95
     '\\;'
    -0.94
     initComponents
    -0.94
    Personensuche
    -0.94
    POSITIVE LOGITS
     and
    0.48
     or
    0.42
     to
    0.41
     
    0.41
     as
    0.38
     in
    0.38
    key
    0.35
     К
    0.34
     //
    0.34
     but
    0.34
    Activations Density 0.946%

    No Known Activations