© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5650
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to political, social, and religious issues, including power structures, historical events, and legal proceedings.

    oai_token-act-pair · gemini-2.0-flash

    -ism suffix

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    }{*}{
    -0.62
     physicist
    -0.60
    Photographer
    -0.58
    scout
    -0.56
     archaeologist
    -0.55
    cleros
    -0.55
    tourist
    -0.54
     gambler
    -0.54
    ARCHITECT
    -0.54
     wrestler
    -0.54
    POSITIVE LOGITS
     ſever
    0.71
     Diſ
    0.70
     Paglinawan
    0.68
     journalism
    0.66
     motherhood
    0.66
     Catholicism
    0.66
    alism
    0.65
     ſtate
    0.65
    UnknownFieldSet
    0.65
     Christianity
    0.64
    Activations Density 6.698%

    No Known Activations