© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4234
    Prev
    Next
    INDEX
    Explanations

    code snippets or file paths

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Monfieur
    -0.61
     themſelves
    -0.59
     myſelf
    -0.59
     Majefty
    -0.59
     himſelf
    -0.57
    CppCodeGen
    -0.57
     lópez
    -0.56
     promouvoir
    -0.56
     purpoſe
    -0.56
     nadzieję
    -0.56
    POSITIVE LOGITS
     województwie
    0.63
    Наводи
    0.60
     beginnetje
    0.60
    nextInt
    0.60
     ISNI
    0.60
     pop
    0.59
    invokeLater
    0.57
    aarrggbb
    0.57
    MigrationBuilder
    0.56
    Autoritní
    0.56
    Activations Density 2.995%

    No Known Activations