© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5847
    Prev
    Next
    INDEX
    Explanations

    verbs in the third person singular, present tense

    oai_token-act-pair · gemini-2.0-flash

    attends

    np_max-act · gemini-2.0-flash

    ending -s

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Serves
    -0.92
    Serves
    -0.90
     evolves
    -0.87
     prepares
    -0.82
     develops
    -0.81
     learns
    -0.81
     settles
    -0.80
     sits
    -0.80
     serves
    -0.79
    serves
    -0.79
    POSITIVE LOGITS
     were
    0.82
     are
    0.67
     weren
    0.63
     have
    0.63
     waren
    0.60
     themselves
    0.57
     były
    0.55
     были
    0.54
    היו
    0.54
    have
    0.53
    Activations Density 2.245%

    No Known Activations