© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 654
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are commonly used when writing software documentation, political commentary, research papers, or restaurant reviews.

    oai_token-act-pair · gemini-2.0-flash

    processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     anywhere
    -0.74
     anytime
    -0.72
     Cualquier
    -0.68
     qualunque
    -0.67
     qualsiasi
    -0.65
     Anywhere
    -0.64
    Anytime
    -0.63
     cualquiera
    -0.63
     Qualquer
    -0.61
     любой
    -0.60
    POSITIVE LOGITS
    expandindo
    0.65
     ['./
    0.63
    ustimmung
    0.55
    otheby
    0.54
    脚注の使い方
    0.51
    تقاوى
    0.51
     nahilalakip
    0.50
     território
    0.46
     pena
    0.46
    рос
    0.45
    Activations Density 2.086%

    No Known Activations