© 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. 7032
    Prev
    Next
    INDEX
    Explanations

    text related to the United Arab Emirates, research programs, and related discussion of water and program leadership

    oai_token-act-pair · gemini-2.0-flash

    terms related to Islam

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

    Islam

    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
    клопе
    -0.59
     StatelessWidget
    -0.57
     watermark
    -0.55
     AppCompat
    -0.54
    enumi
    -0.53
     @"/
    -0.53
    transQ
    -0.52
    didSet
    -0.52
     PropertyChanged
    -0.51
     opérés
    -0.51
    POSITIVE LOGITS
     Islam
    0.62
    Islamic
    0.60
     Islamic
    0.60
     CURIAM
    0.58
     Islamist
    0.55
    Islam
    0.55
     Abubakar
    0.55
    islamic
    0.54
     ISLAM
    0.51
     Rasulullah
    0.51
    Activations Density 3.146%

    No Known Activations