© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11268
    Prev
    Next
    INDEX
    Explanations

    strings of characters commonly found in scientific publications, including math and other symbols, references to equations, and specific formatting conventions

    oai_token-act-pair · gemini-2.0-flash

    random strings/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    UnknownFields
    -0.65
     okuyayım
    -0.62
    UrlResolution
    -0.60
    falgar
    -0.56
    TRIBUN
    -0.54
    Farming
    -0.54
    hankelijk
    -0.52
    gonic
    -0.52
    SBATCH
    -0.50
    RetentionPolicy
    -0.50
    POSITIVE LOGITS
    e
    0.74
    mce
    0.68
     Jayne
    0.67
     DCE
    0.67
     stepmother
    0.65
    wade
    0.65
     Kome
    0.65
     CME
    0.65
    E
    0.64
    ule
    0.64
    Activations Density 2.317%

    No Known Activations