© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1409
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific texts including numbers, equations, and biological and medical terms

    oai_token-act-pair · gemini-2.0-flash

    maximum and minimum values

    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
    Max
    -1.98
     max
    -1.96
    max
    -1.93
     Max
    -1.91
    MAX
    -1.90
     MAX
    -1.85
     Maximum
    -1.69
     Maximal
    -1.61
    Maximum
    -1.57
     maximum
    -1.55
    POSITIVE LOGITS
    OSIS
    0.48
    fert
    0.47
    etheless
    0.47
     Cal
    0.47
     cal
    0.47
    cellation
    0.44
    ielsen
    0.44
    yness
    0.42
    liothèque
    0.42
    BeginContext
    0.42
    Activations Density 2.691%

    No Known Activations