© 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
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 12987
    Prev
    Next
    INDEX
    Explanations

    proper nouns or place names, specifically related to geography, people, and organizations, sometimes in the context of outdoor trails.

    oai_token-act-pair · gemini-2.0-flash

    bridge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     deck
    -0.91
     Deck
    -0.83
    deck
    -0.82
     DECK
    -0.77
     Bridge
    -0.76
     decks
    -0.75
     bridge
    -0.69
    Deck
    -0.69
     BRIDGE
    -0.69
     propOrder
    -0.69
    POSITIVE LOGITS
     kasarigan
    0.75
    ofire
    0.75
    InputBorder
    0.55
     unharmed
    0.54
     bitters
    0.53
    ostante
    0.53
    neté
    0.53
     opérateur
    0.52
    bnf
    0.52
    IBarButtonItem
    0.51
    Activations Density 11.851%

    No Known Activations