© 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. 10451
    Prev
    Next
    INDEX
    Explanations

    code snippets which contain licenses and URLs as well as markups

    oai_token-act-pair · gemini-2.0-flash

    license agreement

    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
     חיצוניים
    -0.67
     juridique
    -0.65
    tvguidetime
    -0.65
     GoogleFonts
    -0.63
    prnewswire
    -0.62
     giuri
    -0.62
    intios
    -0.58
     Psychol
    -0.58
    )|^{
    -0.58
     nuclé
    -0.57
    POSITIVE LOGITS
     surla
    0.61
    شنبه
    0.51
     nearby
    0.51
     walking
    0.48
    glGen
    0.47
    Nearby
    0.46
     local
    0.46
    BeginContext
    0.45
     adjoining
    0.45
     presso
    0.45
    Activations Density 20.498%

    No Known Activations