© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10731
    Prev
    Next
    INDEX
    Explanations

    mentions of community leaders and the community they lead, specifically of the Jewish faith

    oai_token-act-pair · gemini-2.0-flash

    Rabbi

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Jews
    -0.60
     Jewish
    -0.60
    Xna
    -0.58
    <?
    -0.58
     jewish
    -0.57
     BioLib
    -0.55
    таратура
    -0.55
     HTMLElement
    -0.54
    Jewish
    -0.54
     Juden
    -0.54
    POSITIVE LOGITS
     Sha
    0.69
    Sha
    0.67
     Hav
    0.58
     Pes
    0.58
     Sim
    0.57
    formes
    0.56
     سكانية
    0.56
    Pes
    0.56
     Cha
    0.56
     Bar
    0.56
    Activations Density 0.753%

    No Known Activations