© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6919
    Prev
    Next
    INDEX
    Explanations

    first and second person pronouns, and words indicating possibility

    oai_token-act-pair · gemini-2.0-flash

    verbs or actions related to engagement

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

    Questions

    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
     extérieures
    -0.56
     financière
    -0.54
    '][]
    -0.50
     culturelle
    -0.50
     médicaux
    -0.50
     exceptionnelle
    -0.49
     decorativo
    -0.49
     inalámb
    -0.49
     ließen
    -0.49
     humaine
    -0.48
    POSITIVE LOGITS
     hire
    0.75
     spend
    0.73
     يتيمه
    0.73
     join
    0.73
     CreateTagHelper
    0.71
     learn
    0.69
     qualify
    0.69
     standardize
    0.69
    Билгалдахарш
    0.69
     interpret
    0.68
    Activations Density 2.520%

    No Known Activations