© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13844
    Prev
    Next
    INDEX
    Explanations

    the words "cooperate", "cooperation", and "operative".

    oai_token-act-pair · gemini-2.0-flash

    operate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    flashdata
    -0.59
    BarButtonItem
    -0.54
    PostConstruct
    -0.53
    audiovisuel
    -0.51
     furi
    -0.50
     MediatR
    -0.50
    air
    -0.49
    userdetails
    -0.48
    omitempty
    -0.47
    voerd
    -0.47
    POSITIVE LOGITS
     coö
    0.86
     cooperating
    0.86
     kooper
    0.82
     cooperated
    0.81
     cooper
    0.81
     cooperation
    0.80
     cooperate
    0.77
     cooperative
    0.76
    Rohy
    0.73
    cooper
    0.69
    Activations Density 0.797%

    No Known Activations