© 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. 2964
    Prev
    Next
    INDEX
    Explanations

    references to Islamic religious figures and concepts

    oai_token-act-pair · gemini-2.0-flash

    technical or domain-specific terms

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

    Middle Eastern history

    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
     mosques
    -1.12
     Arabic
    -1.07
     mosque
    -1.07
     Islamic
    -1.07
     islamic
    -1.06
     Koran
    -1.06
     Moslem
    -1.05
     Islam
    -1.04
    Islamic
    -1.00
     Islamist
    -0.99
    POSITIVE LOGITS
     referrerpolicy
    0.41
     ges
    0.40
    PopupWindow
    0.35
     Latvi
    0.30
     dor
    0.30
    Enlaces
    0.29
    Lithuan
    0.29
    gdx
    0.29
    篇
    0.29
    df
    0.28
    Activations Density 0.180%

    No Known Activations