© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4783
    Prev
    Next
    INDEX
    Explanations

    text in legal documents related to incidents involving gas pipelines and company names.

    oai_token-act-pair · gemini-2.0-flash

    plumbing and pipes

    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
     समीक्षक
    -0.74
    onAttach
    -0.68
     disconnect
    -0.67
    LookAnd
    -0.62
     OMITBAD
    -0.60
     hose
    -0.60
     taps
    -0.59
     disconnecting
    -0.59
    Obrázky
    -0.59
    Personendaten
    -0.59
    POSITIVE LOGITS
     snippetHide
    0.55
    ategy
    0.52
     itemprop
    0.51
    poptosis
    0.48
     الفيديو
    0.46
    šče
    0.45
    BindingResult
    0.44
    UBL
    0.44
    )))));
    0.44
    ntown
    0.44
    Activations Density 3.728%

    No Known Activations