© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11665
    Prev
    Next
    INDEX
    Explanations

    phrases involving the word "you" or asking for help

    oai_token-act-pair · gemini-2.0-flash

    Addressing the reader

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     NSCoder
    -0.71
    ReusableCell
    -0.68
    DockStyle
    -0.65
     consultato
    -0.63
    ftagPool
    -0.63
    __(/*!
    -0.61
    Kanpo
    -0.58
    مصادر
    -0.58
    MessageTagHelper
    -0.57
    saraba
    -0.57
    POSITIVE LOGITS
    WebServlet
    0.53
    owią
    0.46
    ArgumentParser
    0.43
    arkiv
    0.43
    Eb
    0.43
     Borel
    0.41
     uuidv
    0.41
     protoimpl
    0.39
     thử
    0.39
     Carrying
    0.39
    Activations Density 2.830%

    No Known Activations