© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9906
    Prev
    Next
    INDEX
    Explanations

    mentions of armed conflict and political groups

    oai_token-act-pair · gemini-2.0-flash

    Mai-Mai armed conflict

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Catalytic
    -0.52
     Circular
    -0.50
    flashdata
    -0.50
    djangoproject
    -0.49
    PostExecute
    -0.48
    buku
    -0.47
     Generating
    -0.47
    ptăm
    -0.47
    sendRedirect
    -0.47
     الرياضيه
    -0.47
    POSITIVE LOGITS
    PerformLayout
    0.59
     TimeUnit
    0.52
    醐
    0.51
    帖最后由
    0.49
     يتيمه
    0.49
    toxin
    0.49
     विश्वसनीयता
    0.48
    áculos
    0.47
     ویکی‌آمباردا
    0.47
    ftagPool
    0.46
    Activations Density 1.904%

    No Known Activations