© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2317
    Prev
    Next
    INDEX
    Explanations

    mathematical characters and sequences, especially the tilde symbol and dollar signs surrounding numbers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     numerus
    -0.83
     BrowserModule
    -0.68
    principalTable
    -0.67
    voltaic
    -0.66
    IMON
    -0.66
    hastly
    -0.66
     Viability
    -0.65
     NgModule
    -0.64
    Portale
    -0.63
    quels
    -0.63
    POSITIVE LOGITS
    <bos>
    1.29
    '
    0.48
     the
    0.44
    A
    0.43
    #
    0.42
    /*
    0.41
    ValueStyle
    0.39
    RSpec
    0.38
    -
    0.38
     comigo
    0.37
    Activations Density 0.363%

    No Known Activations