© 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. 15507
    Prev
    Next
    INDEX
    Explanations

    words and phrases describing study or use of something depending on the context

    oai_token-act-pair · gemini-2.0-flash

    technical, scientific

    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
     $_"
    -0.98
     Forumite
    -0.91
    NUMX
    -0.91
     صوتيه
    -0.87
     MainAxisSize
    -0.86
    migrationBuilder
    -0.84
    __(/*!
    -0.84
     ARXIV
    -0.84
    UserScript
    -0.83
    ConstraintMaker
    -0.82
    POSITIVE LOGITS
    ,
    0.46
    .
    0.45
     and
    0.43
     O
    0.42
    Z
    0.41
    Ab
    0.40
    ab
    0.40
     ak
    0.39
     Z
    0.39
    ↵
    0.39
    Activations Density 1.558%

    No Known Activations