© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1682
    Prev
    Next
    INDEX
    Explanations

    words ending in "ist" or similar suffixes related to ideologies, professions, or movements.

    oai_token-act-pair · gemini-2.0-flash

    Political ideologies/categories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    list
    -2.00
     list
    -1.98
     LIST
    -1.65
     lists
    -1.61
    LIST
    -1.59
     List
    -1.50
    lists
    -1.49
     Lists
    -1.46
     Liste
    -1.41
     lista
    -1.38
    POSITIVE LOGITS
    ReusableCell
    0.66
    TestBed
    0.62
     సౌకర్య
    0.58
    verwijspagina
    0.53
     disambiguazione
    0.52
     otomatig
    0.51
     OMITBAD
    0.50
    ImageContext
    0.50
    évaluateur
    0.50
    YourGuide
    0.50
    Activations Density 0.896%

    No Known Activations