© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15012
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to giving, asking for, or receiving advice or help.

    oai_token-act-pair · gemini-2.0-flash

    technical terms or concepts in programming

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

    Programming/Technical content

    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
     générations
    -0.60
     blessés
    -0.60
     étroite
    -0.57
     enfans
    -0.56
     automatiques
    -0.56
    طلحات
    -0.56
     éner
    -0.55
     électroniques
    -0.54
     boissons
    -0.54
     épais
    -0.53
    POSITIVE LOGITS
    SharedDtor
    0.66
    expandindo
    0.66
     resourceCulture
    0.66
    JspWriter
    0.59
     Jezus
    0.52
    DataContract
    0.52
     empiric
    0.52
     Paglinawan
    0.52
    ̀i
    0.52
    UrlResolution
    0.52
    Activations Density 6.323%

    No Known Activations