© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13551
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to military power, technical manufacturing and global, inter-country relations

    oai_token-act-pair · gemini-2.0-flash

    might

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     resourceCulture
    -0.59
    bootstrapcdn
    -0.57
    клопе
    -0.55
    ниципа
    -0.54
    طلحات
    -0.54
    Rüyada
    -0.52
    Powerful
    -0.52
    талья
    -0.52
    ContentAlignment
    -0.52
     Powerful
    -0.50
    POSITIVE LOGITS
     might
    2.47
    might
    2.17
    Might
    2.03
     Might
    1.99
     MIGHT
    1.48
     may
    1.30
     mungkin
    0.99
    may
    0.98
     misschien
    0.93
     vielleicht
    0.84
    Activations Density 2.290%

    No Known Activations