© 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. 12946
    Prev
    Next
    INDEX
    Explanations

    a wide range of proper nouns like people, brands, places, and publications.

    oai_token-act-pair · gemini-2.0-flash

    Proper nouns, names

    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
     disponibilités
    -0.60
    HCM
    -0.60
     pleaſure
    -0.59
    醐
    -0.59
     Majefty
    -0.58
     leaſt
    -0.57
     Normdatei
    -0.57
     Theſe
    -0.56
     poffible
    -0.56
     ſeveral
    -0.56
    POSITIVE LOGITS
     springfox
    0.59
    rrggbb
    0.58
    Xaml
    0.57
     Waray
    0.53
    BrowserModule
    0.53
    GEBURTSDATUM
    0.53
     pila
    0.53
     Sistema
    0.52
     Schuster
    0.52
     waste
    0.52
    Activations Density 5.412%

    No Known Activations