© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11414
    Prev
    Next
    INDEX
    Explanations

    fragments of dialogue or conversation

    oai_token-act-pair · gemini-2.0-flash

    alternatives or contrasts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     myſelf
    -0.73
     itſelf
    -0.68
    ISupport
    -0.63
    addCriterion
    -0.63
     leſs
    -0.63
     '\\;'
    -0.63
     heiress
    -0.60
     trajets
    -0.60
     himſelf
    -0.59
     Shakspeare
    -0.59
    POSITIVE LOGITS
    EnableWeb
    0.50
     CreateTagHelper
    0.47
     colspan
    0.45
    遂
    0.41
    ioc
    0.41
    ambique
    0.40
    ([
    0.40
     rowspan
    0.40
    fastjson
    0.39
     InputDecoration
    0.39
    Activations Density 2.706%

    No Known Activations