© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1417
    Prev
    Next
    INDEX
    Explanations

    terms related to war, military and service

    oai_token-act-pair · gemini-2.0-flash

    war

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    const
    -0.50
     Constitucional
    -0.42
    istoitu
    -0.41
     soient
    -0.40
     cabra
    -0.39
    colar
    -0.38
     hayvan
    -0.38
    Hate
    -0.38
    Formik
    -0.37
    當然
    -0.37
    POSITIVE LOGITS
     ChromeDriver
    0.70
    منابع
    0.68
    elter
    0.67
    новништво
    0.66
    GEBURTSDATUM
    0.66
    GeneratedCode
    0.65
     Wav
    0.65
    amins
    0.65
     الحره
    0.63
     endregion
    0.63
    Activations Density 1.742%

    No Known Activations