© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 25
    Prev
    Next
    INDEX
    Explanations

    text describing the Holocaust and Nazi Germany, including the deaths of Jews, Croats, and others in concentration camps.

    oai_token-act-pair · gemini-2.0-flash

    Nazi regime and camps

    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
     تعدى
    -0.60
    findpost
    -0.55
     BrowserModule
    -0.51
    OrBuilder
    -0.50
    ExtendWith
    -0.48
     Medio
    -0.46
    Datuak
    -0.45
    LoggerFactory
    -0.45
     kellett
    -0.44
     Erişim
    -0.43
    POSITIVE LOGITS
    CloseOperation
    0.62
    ="@+
    0.57
     Jefus
    0.56
     itſelf
    0.55
     Theſe
    0.54
    wiſe
    0.52
    Sport
    0.51
     becauſe
    0.51
    osexual
    0.50
    eſ
    0.50
    Activations Density 3.542%

    No Known Activations