© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15515
    Prev
    Next
    INDEX
    Explanations

    words related to countries and geopolitics, especially involving wars, armies and the soviet union.

    oai_token-act-pair · gemini-2.0-flash

    History/geography

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     enfans
    -0.58
    IVOS
    -0.50
     négo
    -0.49
    entiated
    -0.49
    holdet
    -0.48
     fidé
    -0.48
    ouz
    -0.48
    ньше
    -0.47
     waters
    -0.47
     nuovamente
    -0.47
    POSITIVE LOGITS
    CppCodeGen
    0.60
    raulic
    0.54
     محفوظة
    0.54
    GIVEREF
    0.53
    ViewFeatures
    0.53
     WaitForSeconds
    0.52
    клопе
    0.52
     通販
    0.51
    mybatisplus
    0.51
     церкви
    0.49
    Activations Density 0.759%

    No Known Activations