© 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. 9772
    Prev
    Next
    INDEX
    Explanations

    words conveying reasoning, communication and agreement

    oai_token-act-pair · gemini-2.0-flash

    say "that"

    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
    which
    -1.34
    Which
    -1.29
     Which
    -1.15
     WHICH
    -1.04
    quelles
    -0.96
     οποία
    -0.93
     laquelle
    -0.90
     οποίο
    -0.85
    quels
    -0.84
    hich
    -0.81
    POSITIVE LOGITS
     that
    2.20
     rằng
    0.95
     bahwa
    0.88
     że
    0.72
     ότι
    0.72
     propOrder
    0.66
     कि
    0.63
    multirow
    0.62
     kwamba
    0.60
     mà
    0.58
    Activations Density 0.694%

    No Known Activations