© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3633
    Prev
    Next
    INDEX
    Explanations

    terms used in academic publications and software licenses

    oai_token-act-pair · gemini-2.0-flash

    Foundation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     defaultstate
    -0.73
     ModelExpression
    -0.65
    (!__
    -0.58
     ISNI
    -0.57
    atguigu
    -0.54
     titolata
    -0.54
     fallu
    -0.50
    findpost
    -0.49
    PDATE
    -0.49
    gebob
    -0.48
    POSITIVE LOGITS
    ſelves
    0.74
     itſelf
    0.69
    ſelf
    0.67
    ❋
    0.67
    <bos>
    0.65
    neſs
    0.62
     purpoſe
    0.60
    queryInterface
    0.60
    Amicalement
    0.59
     userSchema
    0.59
    Activations Density 8.248%

    No Known Activations