© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13382
    Prev
    Next
    INDEX
    Explanations

    technical terms, especially in medical and computer science fields

    oai_token-act-pair · gemini-2.0-flash

    technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.93
    +:+
    -0.70
     незавершена
    -0.67
     فريبيس
    -0.66
    ChildScrollView
    -0.59
     typelib
    -0.58
    Brainz
    -0.57
    AddTagHelper
    -0.51
    বহ
    -0.51
    ElementException
    -0.50
    POSITIVE LOGITS
     Efq
    0.59
    tvguidetime
    0.56
     ſtate
    0.53
     fevere
    0.53
     houſe
    0.52
    
    0.50
    UnusedPrivate
    0.50
     uſed
    0.48
     Ulf
    0.47
     chofe
    0.46
    Activations Density 9.952%

    No Known Activations