© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8500
    Prev
    Next
    INDEX
    Explanations

    words or phrases connoting teams of humans working together

    oai_token-act-pair · gemini-2.0-flash

    Colors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    __':
    -0.50
    __":
    -0.48
    Abitanti
    -0.44
    principalTable
    -0.41
     kasarigan
    -0.41
    __':
    -0.40
    PickerController
    -0.40
    āci
    -0.40
     powierzch
    -0.39
     ripar
    -0.39
    POSITIVE LOGITS
     blue
    1.71
     green
    1.63
     yellow
    1.61
     red
    1.48
     purple
    1.45
    blue
    1.42
    green
    1.41
    yellow
    1.41
     white
    1.41
     orange
    1.39
    Activations Density 1.007%

    No Known Activations