© 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. 5058
    Prev
    Next
    INDEX
    Explanations

    words or symbols in scientific notation and technical diagrams

    oai_token-act-pair · gemini-2.0-flash

    non-English terms or specialized jargon

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

    foreign words

    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
     is
    -0.52
     découver
    -0.46
     éprou
    -0.45
     scheda
    -0.42
     démon
    -0.42
     kanssa
    -0.41
    ménage
    -0.41
     renfor
    -0.41
     tiens
    -0.41
     discussione
    -0.41
    POSITIVE LOGITS
     disambiguazione
    0.89
    Vidite
    0.75
    iocene
    0.75
     NSCoder
    0.74
    ThroughAttribute
    0.73
     CURIAM
    0.72
    StoryboardSegue
    0.71
     Efq
    0.69
    новниш
    0.68
    homonymie
    0.68
    Activations Density 5.043%

    No Known Activations