© 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. 7783
    Prev
    Next
    INDEX
    Explanations

    words related to authority, government, police, and politics in Africa

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating serious crimes or incidents

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

    institutions

    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
    TintMode
    -0.71
    脚注の使い方
    -0.65
    contentLoaded
    -0.63
    TSCA
    -0.63
     فريبيس
    -0.61
     betweenstory
    -0.60
    التالي
    -0.59
     Monfieur
    -0.56
     kaarangay
    -0.56
    GraphicsUnit
    -0.56
    POSITIVE LOGITS
    طاء
    0.57
    Vidite
    0.50
     du
    0.50
     hallaz
    0.49
    hbar
    0.49
     Present
    0.46
     <<<<<<<<<<<<<<
    0.46
    TagMode
    0.46
     cup
    0.46
     tros
    0.46
    Activations Density 16.833%

    No Known Activations