© 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. 9211
    Prev
    Next
    INDEX
    Explanations

    words related to conflict, crime, money, and organizations

    oai_token-act-pair · gemini-2.0-flash

    News article 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
    enterOuterAlt
    -0.52
    ándote
    -0.50
    Paginator
    -0.47
     gynhyrchwyd
    -0.46
     PARTNER
    -0.46
     gênero
    -0.46
     associés
    -0.45
     meilleures
    -0.44
     يتيمه
    -0.44
     pubblicità
    -0.43
    POSITIVE LOGITS
    TagMode
    0.77
     jScrollPane
    0.76
    tonode
    0.62
     '\\;'
    0.60
    رشف
    0.60
    はじめに
    0.59
     ErrIntOverflow
    0.58
    siella
    0.58
     désolés
    0.56
    fromnode
    0.54
    Activations Density 3.128%

    No Known Activations