© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8078
    Prev
    Next
    INDEX
    Explanations

    code related to variable names and array indexing

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
    AddTagHelper
    -0.94
    OGND
    -0.91
    StructEnd
    -0.83
    AccessorTable
    -0.81
     >=",
    -0.80
     StatelessWidget
    -0.79
     Wiktionnaire
    -0.77
     Jefus
    -0.76
    énario
    -0.75
     AssemblyCompany
    -0.74
    POSITIVE LOGITS
    )
    0.52
    }
    0.48
    ]!='
    0.43
    can
    0.41
    ]
    0.40
    ]<<"
    0.39
    Can
    0.39
    ]<=
    0.38
     Can
    0.37
    Make
    0.37
    Activations Density 1.518%

    No Known Activations