© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5434
    Prev
    Next
    INDEX
    Explanations

    content loosely related to the Satmar Jewish community and rabbis, and possibly also to speech

    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_18/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.18.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
    prechpartner
    -0.58
     جغرافيا
    -0.56
     Himo
    -0.53
    IUrlHelper
    -0.53
    bewerken
    -0.51
     estimés
    -0.50
     retiring
    -0.50
     Retired
    -0.49
     hered
    -0.48
     geográfica
    -0.48
    POSITIVE LOGITS
     Jewish
    0.87
     Rabbi
    0.75
    Jewish
    0.71
     Jews
    0.70
     kosher
    0.69
     jewish
    0.69
     synag
    0.68
     rabbi
    0.67
    Rabbi
    0.64
     Baruch
    0.64
    Activations Density 1.188%

    No Known Activations