© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8466
    Prev
    Next
    INDEX
    Explanations

    mentions of military units, bases, and operations

    oai_token-act-pair · gemini-2.0-flash

    Air force bases

    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
    ucher
    -0.51
    VolleyError
    -0.50
    CodeDom
    -0.48
    enste
    -0.48
     mergeFrom
    -0.48
    towany
    -0.46
    تفصیلات
    -0.46
    Preced
    -0.45
    CreateMap
    -0.45
    mapStateToProps
    -0.45
    POSITIVE LOGITS
    webElementXpaths
    0.79
    +#+#
    0.69
    titleMargin
    0.69
    WarningLevel
    0.67
    κτηρισ
    0.59
    MemoryWarning
    0.59
    maxcdn
    0.59
    abestanden
    0.55
     cherchés
    0.54
    enumerable
    0.54
    Activations Density 1.703%

    No Known Activations