© 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. 4562
    Prev
    Next
    INDEX
    Explanations

    words that emphasize or qualify other words and phrases, like "especially", "very", "rather".

    oai_token-act-pair · gemini-2.0-flash

    especially/particularly

    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
    QMetaType
    -0.74
     Because
    -0.73
    Because
    -0.69
     Whose
    -0.66
    CPtr
    -0.66
     And
    -0.65
     When
    -0.65
    rawDesc
    -0.63
    Whose
    -0.63
     and
    -0.62
    POSITIVE LOGITS
    PRNewswire
    0.56
     attenuated
    0.56
    ercice
    0.52
    žová
    0.49
    atyana
    0.49
    dây
    0.48
     encapsulated
    0.48
     settlement
    0.48
    polation
    0.48
    jestel
    0.47
    Activations Density 30.130%

    No Known Activations