© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14915
    Prev
    Next
    INDEX
    Explanations

    words related to political conflict in the Middle East

    oai_token-act-pair · gemini-2.0-flash

    geographical political elements

    np_token-act-pair-logits · gpt-4o-mini

    Global politics/world events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     مشين
    -0.67
     Paglinawan
    -0.65
     ThemeData
    -0.62
     AssemblyTitle
    -0.61
    inaison
    -0.60
     <=",
    -0.60
    enderror
    -0.58
     ControllerBase
    -0.57
    kloped
    -0.57
    messageInfo
    -0.56
    POSITIVE LOGITS
    bakan
    0.46
    ẾT
    0.45
    IVEREF
    0.45
    قایناق‌لار
    0.43
    miede
    0.42
    voort
    0.41
     Discovery
    0.41
     purpure
    0.40
    θη
    0.40
     ConstraintSet
    0.40
    Activations Density 1.324%

    No Known Activations