© 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. 12029
    Prev
    Next
    INDEX
    Explanations

    numerical values related to buildings or constructions

    oai_token-act-pair · gemini-2.0-flash

    Buildings

    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
     building
    -2.52
     Building
    -2.42
    Building
    -2.39
     buildings
    -2.36
    building
    -2.33
     BUILDING
    -2.28
     build
    -2.25
     Buildings
    -2.25
    buildings
    -2.22
    BUILDING
    -2.17
    POSITIVE LOGITS
    UnsafeEnabled
    0.65
    oredCriteria
    0.54
    dataTables
    0.53
     ویکی‌پدی
    0.52
    ṳ
    0.52
    SqlSession
    0.50
     Codable
    0.50
    ConfigureAwait
    0.50
     aange
    0.49
     createSlice
    0.49
    Activations Density 1.714%

    No Known Activations