© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14082
    Prev
    Next
    INDEX
    Explanations

    expressions of emotion that act as discourse markers

    oai_token-act-pair · gemini-2.0-flash

    Introductions or examples

    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
     thereto
    -0.61
    Filmographie
    -0.51
     Audiodateien
    -0.50
    "}")
    -0.48
    )>>
    -0.47
    ]<<
    -0.46
    galkan
    -0.45
    というと
    -0.44
    ته
    -0.44
     ostavi
    -0.43
    POSITIVE LOGITS
     did
    2.28
     Did
    2.22
    Did
    2.20
    did
    2.11
    DID
    1.67
     DID
    1.64
    Have
    0.88
     Have
    0.83
    Avez
    0.82
    Didn
    0.81
    Activations Density 1.486%

    No Known Activations