© 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. 4558
    Prev
    Next
    INDEX
    Explanations

    words indicating commonness and purpose

    oai_token-act-pair · gemini-2.0-flash

    references in various languages

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

    Often/Sometimes

    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
     often
    -2.63
     usually
    -2.58
    usually
    -2.38
    often
    -2.33
     Often
    -2.33
    Often
    -2.27
    Usually
    -2.25
     typically
    -2.23
     Usually
    -2.22
     spesso
    -2.08
    POSITIVE LOGITS
     AssemblyCulture
    0.81
    참고
    0.65
    ioneer
    0.60
    Referències
    0.59
     Référence
    0.59
     arşivlendi
    0.57
    ReusableCell
    0.57
    嘩
    0.55
    afficheront
    0.53
    Примечания
    0.53
    Activations Density 6.913%

    No Known Activations