© 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. 3277
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to Scandinavian languages and culture

    oai_token-act-pair · gemini-2.0-flash

    Legal documents/motions

    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
     af
    -0.68
    ighed
    -0.60
     op
    -0.59
    ud
    -0.54
    BuildContext
    -0.53
     ud
    -0.52
    Referencer
    -0.50
    op
    -0.49
     ful
    -0.48
    ligt
    -0.48
    POSITIVE LOGITS
    ThemeOverlay
    0.58
    openzeppelin
    0.57
     magát
    0.57
    ercito
    0.57
     godk
    0.56
     tartalmaz
    0.55
    csolódó
    0.55
    árbol
    0.55
    niająca
    0.54
    isNameExpr
    0.53
    Activations Density 0.745%

    No Known Activations