© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3708
    Prev
    Next
    INDEX
    Explanations

    articles such as "the", "a", and "their" as well as references to Marvel.

    oai_token-act-pair · gemini-2.0-flash

    the

    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
    thâu
    -0.49
    routeProvider
    -0.47
     estekak
    -0.46
    siem
    -0.44
    omitempty
    -0.44
    InjectMocks
    -0.44
    CompleteListener
    -0.44
    */].
    -0.43
    sivité
    -0.43
    Спасылкі
    -0.43
    POSITIVE LOGITS
    fromCharCode
    0.68
     montes
    0.58
     dál
    0.57
    IsContent
    0.55
    fo
    0.55
    ########.
    0.55
     šaty
    0.54
    XtraGrid
    0.54
    ltä
    0.54
    Bibliograf
    0.54
    Activations Density 2.467%

    No Known Activations