© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14422
    Prev
    Next
    INDEX
    Explanations

    fragments of French in an English context related to internet use and knowing about software

    oai_token-act-pair · gemini-2.0-flash

    Future tense

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     would
    -0.93
    would
    -0.78
    InjectAttribute
    -0.76
    Would
    -0.76
     sarebbe
    -0.75
     sarebbero
    -0.74
     zouden
    -0.74
     Would
    -0.72
     serait
    -0.68
     skulle
    -0.68
    POSITIVE LOGITS
     will
    1.39
    will
    1.18
    Will
    1.05
     Will
    1.00
     shall
    0.88
     WILL
    0.87
     akan
    0.75
    WILL
    0.74
    shall
    0.71
    Será
    0.71
    Activations Density 1.734%

    No Known Activations