© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7627
    Prev
    Next
    INDEX
    Explanations

    source code related to properties in Kotlin

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
    GEBURTSDATUM
    -0.98
    ModelAdmin
    -0.88
    fortawesome
    -0.86
     تضيفلها
    -0.85
    SpringBootTest
    -0.82
    twimg
    -0.80
     convertView
    -0.78
    ":[{
    -0.75
    ReusableCell
    -0.75
    SerializedSize
    -0.74
    POSITIVE LOGITS
    inna
    0.33
     over
    0.32
    over
    0.32
     sembra
    0.31
    overs
    0.30
    قاب
    0.30
    клопе
    0.28
     pare
    0.28
    Over
    0.28
     qualified
    0.27
    Activations Density 2.922%

    No Known Activations