© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6657
    Prev
    Next
    INDEX
    Explanations

    language expressing potential or causation

    oai_token-act-pair · gemini-2.0-flash

    due, because

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     وتسجيلات
    -0.56
    hoeddwyd
    -0.50
    {§
    -0.48
    defineProperty
    -0.45
     समीक्षाओं
    -0.44
     nonatomic
    -0.43
    ttes
    -0.42
    Datuak
    -0.42
     orm
    -0.42
    )$_
    -0.41
    POSITIVE LOGITS
     due
    1.92
     because
    1.77
    due
    1.65
     debido
    1.63
     devido
    1.50
    because
    1.47
    Due
    1.41
     vanwege
    1.41
     owing
    1.39
     بسبب
    1.38
    Activations Density 2.423%

    No Known Activations