© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 9417
    Prev
    Next
    INDEX
    Explanations

    LaTeX math mode environments and associated syntax

    oai_token-act-pair · gemini-2.0-flash

    mathematical 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
     }}=
    -0.80
    }=
    -0.77
    }}=
    -0.76
    )}=
    -0.73
    })=
    -0.73
    ]]=
    -0.72
    )}+\
    -0.72
    =“
    -0.71
     }=
    -0.70
    )+\
    -0.69
    POSITIVE LOGITS
    ValueGeneration
    0.48
     &
    0.47
    elemField
    0.45
    rungsseite
    0.44
    haustible
    0.43
     føl
    0.42
    uolo
    0.40
    InteropServices
    0.39
    ponential
    0.39
    )&
    0.38
    Activations Density 1.506%

    No Known Activations