© 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. 12809
    Prev
    Next
    INDEX
    Explanations

    bracketed numbers, likely references

    oai_token-act-pair · gemini-2.0-flash

    unusual word patterns or foreign language tokens

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

    Reference to papers

    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
    kloped
    -0.58
    ))[
    -0.58
    исленность
    -0.57
    IUrlHelper
    -0.54
    ">[
    -0.54
    matchCondition
    -0.54
    addContainerGap
    -0.54
    生平
    -0.52
    minecraftforge
    -0.52
     [
    -0.51
    POSITIVE LOGITS
     suyo
    0.55
     مشين
    0.55
    Chham
    0.54
     whither
    0.52
    ilitatea
    0.51
    albero
    0.48
    forKey
    0.47
    abbé
    0.47
     kolye
    0.47
    DotNetBar
    0.47
    Activations Density 2.547%

    No Known Activations