© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4800
    Prev
    Next
    INDEX
    Explanations

    words associated with cognitive tests and scientific studies

    oai_token-act-pair · gemini-2.0-flash

    cognitive performance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    šanai
    -0.50
     uVar
    -0.50
    urto
    -0.49
    spyOn
    -0.49
     RequestMethod
    -0.48
    pushFollow
    -0.48
    ulence
    -0.47
    mybatisplus
    -0.47
    วัติ
    -0.47
     Atmosphäre
    -0.47
    POSITIVE LOGITS
     jsPsych
    0.65
    +#+#
    0.64
     CreateTagHelper
    0.64
     للاسماء
    0.63
    isContained
    0.58
    IContainer
    0.53
     Biblia
    0.50
    ंदीखरीदारी
    0.50
    fromnode
    0.50
    Попис
    0.50
    Activations Density 2.266%

    No Known Activations