© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7583
    Prev
    Next
    INDEX
    Explanations

    words or phrases that indicate an explanation, qualification, or expansion on a previous statement or idea.

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     he
    -1.54
     EconPapers
    -0.98
    SharedCtor
    -0.90
     он
    -0.84
     그는
    -0.75
    XmlAccessorType
    -0.75
    Personensuche
    -0.74
    TypedDataSet
    -0.74
    AsUp
    -0.74
    oredCriteria
    -0.73
    POSITIVE LOGITS
     under
    0.58
    under
    0.56
     for
    0.55
     it
    0.54
    no
    0.53
     no
    0.47
     aspetti
    0.46
    ga
    0.45
    gt
    0.45
    jo
    0.44
    Activations Density 22.799%

    No Known Activations