© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2868
    Prev
    Next
    INDEX
    Explanations

    mentions of prisoners of war and related subjects like the Soviet Union, war, and Finnish relations.

    oai_token-act-pair · gemini-2.0-flash

    POW

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    windowFixed
    -0.70
    fjspx
    -0.57
    verwijspagina
    -0.50
    +#+#
    -0.48
    ecm
    -0.47
     समीक्षाओं
    -0.47
    istisches
    -0.47
    postDelayed
    -0.45
    üyada
    -0.45
    userdetails
    -0.45
    POSITIVE LOGITS
     ويكيميديا
    0.62
     intptr
    0.61
    takings
    0.60
    épendance
    0.56
    hilation
    0.55
     Dernière
    0.53
     stappen
    0.53
    ambilan
    0.52
    plyr
    0.52
    delwed
    0.51
    Activations Density 3.474%

    No Known Activations