© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15284
    Prev
    Next
    INDEX
    Explanations

    multiple different types of online videos, including encoding/decoding and flowers

    oai_token-act-pair · gemini-2.0-flash

    Code/programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Are
    -0.93
     Are
    -0.82
    Than
    -0.79
    Is
    -0.78
     quæ
    -0.74
    LookAnd
    -0.73
     utafitiHapana
    -0.73
    Ok
    -0.72
    Into
    -0.72
    Or
    -0.71
    POSITIVE LOGITS
    SqlClient
    0.59
    _();
    0.57
    XmlAccessType
    0.56
     javafx
    0.53
    ]){
    0.50
     GlobalKey
    0.48
    htaccess
    0.47
    ParallelGroup
    0.46
    iostream
    0.46
     uuidv
    0.45
    Activations Density 2.547%

    No Known Activations