© 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. 5242
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    special characters and code-like syntax

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

    Code/math

    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
      
    -0.95
    ","
    -0.76
    “
    -0.76
    nt
    -0.74
    <em>
    -0.73
    as
    -0.70
    <strong>
    -0.69
    V
    -0.69
    «
    -0.69
    <i>
    -0.68
    POSITIVE LOGITS
    ^(@)
    1.47
     Efq
    1.27
     ")
    1.24
    )";
    1.23
    NUMX
    1.23
     >",
    1.22
    "])
    1.22
     "));
    1.21
    >\<^
    1.20
     ]
    1.19
    Activations Density 5.875%

    No Known Activations