© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8343
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a current state of being or becoming

    oai_token-act-pair · gemini-2.0-flash

    processes of change or growth

    np_token-act-pair-logits · gpt-4o-mini

    the ending "-ing"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     الحره
    -0.59
     Biôgrafia
    -0.57
    ctivos
    -0.53
     vulgaires
    -0.52
    ={({
    -0.50
    StackNavigator
    -0.50
    存于互联网档案馆
    -0.49
    ypus
    -0.48
    RectangleBorder
    -0.48
     thermique
    -0.48
    POSITIVE LOGITS
     becoming
    0.99
     gaining
    0.84
     proving
    0.81
     joining
    0.77
     getting
    0.74
    becoming
    0.74
     receiving
    0.72
     telling
    0.72
     having
    0.71
     saying
    0.70
    Activations Density 1.053%

    No Known Activations