© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4226
    Prev
    Next
    INDEX
    Explanations

    PHP code snippets and related information

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     оригіналу
    -0.91
     дописавши
    -0.70
    parsedMessage
    -0.60
    évaluateur
    -0.57
     ویکی‌پدیا
    -0.56
    prepareStatement
    -0.53
     становника
    -0.48
    anglès
    -0.48
    ędzie
    -0.47
    ことにしました
    -0.47
    POSITIVE LOGITS
    StoryboardSegue
    0.63
    chọn
    0.59
    DrawerToggle
    0.57
    oa̍t
    0.57
    ContentAsync
    0.56
    endphp
    0.54
     الرياضيه
    0.54
    LLocation
    0.51
    zeitige
    0.50
    neter
    0.50
    Activations Density 0.643%

    No Known Activations