© 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. 1011
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    mathematics and code 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
    GOTREF
    -0.73
    onViewCreated
    -0.66
    listFiles
    -0.64
    }
    -0.63
    StoreMessageInfo
    -0.61
    ApiModelProperty
    -0.60
    saraba
    -0.60
    iertas
    -0.59
     redé
    -0.59
    ️
    -0.57
    POSITIVE LOGITS
     }\
    0.77
    )\
    0.64
    ]\
    0.63
    })\
    0.60
    MessageTagHelper
    0.58
     }}\
    0.58
    ))\
    0.57
    }\
    0.56
    ]}\
    0.54
    )}\
    0.52
    Activations Density 3.731%

    No Known Activations