© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13487
    Prev
    Next
    INDEX
    Explanations

    CSS code snippets

    oai_token-act-pair · gemini-2.0-flash

    snippets of code or markup syntax

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

    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_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
     defaultstate
    -0.49
    vantaged
    -0.49
    En
    -0.47
    contentLoaded
    -0.47
     En
    -0.46
     anzu
    -0.45
     sm
    -0.45
    readystatechange
    -0.44
     Mil
    -0.44
    ↵
    -0.44
    POSITIVE LOGITS
    ")));
    0.68
    '])){
    0.66
    ^(@)
    0.65
    )++;
    0.60
    NUMX
    0.59
     Vikipedi
    0.57
     AppColors
    0.57
     itſelf
    0.56
    ".
    0.55
     "\<
    0.55
    Activations Density 2.619%

    No Known Activations