© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8274
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs, conjunctions, and linking words that express relationships between clauses, along with related qualifiers and intensifiers.

    oai_token-act-pair · gemini-2.0-flash

    Technical descriptions

    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
    Negative Logits
    StoryboardSegue
    -0.62
     dAtA
    -0.61
    crollView
    -0.59
    bleed
    -0.56
     gård
    -0.53
     gynhyrchwyd
    -0.52
    UnitTesting
    -0.51
    AZINE
    -0.49
    tvguidetime
    -0.49
    XmlAccessorType
    -0.49
    POSITIVE LOGITS
    ArrowToggle
    0.56
    WriteTagHelper
    0.54
    loài
    0.52
    嘧
    0.52
     للتو
    0.52
    脚注の使い方
    0.49
     kilometres
    0.47
    Carriera
    0.47
    Autoritní
    0.47
     superior
    0.46
    Activations Density 0.825%

    No Known Activations