© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12729
    Prev
    Next
    INDEX
    Explanations

    anti-semitic statements

    oai_token-act-pair · gemini-2.0-flash

    Antisemitism and Jewish references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Jewish
    -2.00
    Jewish
    -1.73
     Jews
    -1.62
     jewish
    -1.59
     Israeli
    -1.59
     Israel
    -1.53
     jüdis
    -1.48
    Israeli
    -1.44
     Jew
    -1.43
     Hebrew
    -1.42
    POSITIVE LOGITS
    karl
    0.54
     Mant
    0.47
     Sult
    0.45
    Schedulers
    0.44
    acidad
    0.44
     Kett
    0.43
    spo
    0.43
    (:,:,
    0.43
     Chlor
    0.42
     Hout
    0.41
    Activations Density 1.634%

    No Known Activations