© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14640
    Prev
    Next
    INDEX
    Explanations

    words associated with events and locations within a narrative

    oai_token-act-pair · gemini-2.0-flash

    was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    новништво
    -0.59
     géographique
    -0.59
    setArguments
    -0.54
    anging
    -0.49
     المعيارى
    -0.49
     betweenstory
    -0.48
    pon
    -0.48
    ########.
    -0.46
     stratégies
    -0.46
    ʃ
    -0.46
    POSITIVE LOGITS
    Rüyada
    0.63
     leased
    0.61
    CppMethod
    0.59
     occupied
    0.58
     dyna
    0.56
     skimmed
    0.54
    Scénario
    0.52
     uska
    0.52
    ">'.$
    0.52
     noqa
    0.51
    Activations Density 1.576%

    No Known Activations