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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4206
    Prev
    Next
    INDEX
    Explanations

    mentions of Iran and US foreign policy, particularly regime change

    oai_token-act-pair · gemini-2.0-flash

    Iran and Iranian

    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
     IR
    -1.63
     Iranian
    -1.57
     Iran
    -1.55
     Ir
    -1.50
    IR
    -1.41
    Iran
    -1.38
    Ir
    -1.30
     ir
    -1.29
     iran
    -1.28
    Iranian
    -1.27
    POSITIVE LOGITS
    colage
    0.49
    fastjson
    0.48
    afterEach
    0.47
    ceny
    0.47
     CNA
    0.47
     supreme
    0.46
     Manoj
    0.46
     AppComponent
    0.45
    supreme
    0.45
    tableFuture
    0.45
    Activations Density 1.615%

    No Known Activations