© 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. 10997
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages associated with rankings in sports or political contests

    oai_token-act-pair · gemini-2.0-flash

    with

    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
    ViewFeatures
    -0.57
    LEncoder
    -0.55
     contextLoads
    -0.51
    uxxxx
    -0.47
    ContentLoaded
    -0.47
     Löwen
    -0.46
    GPS
    -0.45
    Diweddarwch
    -0.44
    prima
    -0.44
    مصادر
    -0.43
    POSITIVE LOGITS
    httphttps
    0.67
    ostante
    0.63
    gameserver
    0.63
    lapsingToolbar
    0.62
    runApp
    0.58
    EClass
    0.56
     ApiException
    0.56
    Demografía
    0.56
    batore
    0.55
    rachtet
    0.54
    Activations Density 0.799%

    No Known Activations