© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15230
    Prev
    Next
    INDEX
    Explanations

    titles, locations, organizations, and dates and names in the text, particularly those related to Thailand and India

    oai_token-act-pair · gemini-2.0-flash

    mixed text snippets

    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
    SharedDtor
    -0.71
    LayoutStyle
    -0.62
     Савезне
    -0.58
    脚注の使い方
    -0.52
    GenerationType
    -0.50
    GEBURTS
    -0.49
     Bress
    -0.48
     oprot
    -0.47
     Californie
    -0.47
    ennies
    -0.47
    POSITIVE LOGITS
    MENAFN
    0.63
    SourceChecksum
    0.60
    JAKARTA
    0.59
    lamabad
    0.57
    bilisi
    0.57
     referrerpolicy
    0.56
    Qur
    0.55
     Khmer
    0.55
    paksa
    0.54
     Nehru
    0.52
    Activations Density 25.523%

    No Known Activations