© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13228
    Prev
    Next
    INDEX
    Explanations

    numbers, arithmetic and rates

    oai_token-act-pair · gemini-2.0-flash

    technical content/data processing

    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
     each
    -1.66
    each
    -1.61
    Each
    -1.60
     Each
    -1.48
    EACH
    -1.36
     EACH
    -1.28
     chaque
    -1.13
    每
    -1.08
     every
    -1.02
     каждый
    -1.02
    POSITIVE LOGITS
    Vanjske
    0.58
    XtraGrid
    0.58
    قایناقلار
    0.54
    Референце
    0.54
    MessageTagHelper
    0.54
    LECTIONS
    0.53
    DNS
    0.52
    ätie
    0.52
    craper
    0.51
    psack
    0.51
    Activations Density 3.681%

    No Known Activations