© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12236
    Prev
    Next
    INDEX
    Explanations

    source code

    oai_token-act-pair · gemini-2.0-flash

    programming language syntax and special characters

    np_token-act-pair-logits · gpt-4o-mini

    code terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    <eos>
    -0.50
     L
    -0.48
    Datuak
    -0.47
     hinaus
    -0.47
    hem
    -0.47
     hem
    -0.46
     G
    -0.45
     Can
    -0.44
    casecmp
    -0.44
     g
    -0.43
    POSITIVE LOGITS
    principalColumn
    0.97
     pleaſure
    0.78
    يكب
    0.75
     ſche
    0.74
     '\\;'
    0.70
    ſelves
    0.70
     AssemblyCulture
    0.70
     itſelf
    0.70
    UnusedPrivate
    0.70
    ſelf
    0.70
    Activations Density 2.569%

    No Known Activations