© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 5744
    Prev
    Next
    INDEX
    Explanations

    the substring 'mathrm' followed by a number

    oai_token-act-pair · gemini-2.0-flash

    math notation

    np_max-act-logits · 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
    })$}
    -0.91
    ագրություններ
    -0.84
    .")]
    -0.78
     AssemblyTitle
    -0.73
    RTEX
    -0.73
     }}"></
    -0.73
    ThroughAttribute
    -0.72
    )?;
    -0.71
    ']))
    
    -0.71
    '])){
    
    -0.71
    POSITIVE LOGITS
     sub
    0.45
     liquid
    0.42
    thaf
    0.42
     occhi
    0.42
    sub
    0.40
    bagai
    0.40
     ojo
    0.40
     societ
    0.39
    V
    0.39
     Coates
    0.39
    Activations Density 0.689%

    No Known Activations