© 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. 13327
    Prev
    Next
    INDEX
    Explanations

    mentions of computer libraries and library-related terms like "link", "shared", or "libc"

    oai_token-act-pair · gemini-2.0-flash

    library references

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

    lib

    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
    TagHelper
    -0.63
    Tags
    -0.54
     En
    -0.52
    alable
    -0.52
    uminate
    -0.52
    Carriera
    -0.51
    Linki
    -0.50
    cipes
    -0.49
    glers
    -0.49
    pendi
    -0.47
    POSITIVE LOGITS
     '\\;'
    0.57
    AndEndTag
    0.57
    zzleHttp
    0.56
     Taktlose
    0.56
    TagMode
    0.55
    aarrggbb
    0.55
     initComponents
    0.54
    stdc
    0.54
    TintMode
    0.53
    windowFixed
    0.53
    Activations Density 1.141%

    No Known Activations