© 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. 9437
    Prev
    Next
    INDEX
    Explanations

    code headers indicating the creation and copyright information of a file

    oai_token-act-pair · gemini-2.0-flash

    by

    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
     linkovi
    -0.69
     tartalomajánló
    -0.66
     noqa
    -0.63
    Kaynakça
    -0.61
     snippetHide
    -0.60
    tableFuture
    -0.60
    Manbalar
    -0.58
    Искәрмәләр
    -0.57
    Referanser
    -0.54
    βάλ
    -0.54
    POSITIVE LOGITS
    UnknownFields
    0.62
    BeginInit
    0.59
    <tbody>
    0.53
    sidemargin
    0.53
    enumii
    0.52
    GEBURTSDATUM
    0.51
     CreateTagHelper
    0.49
    ästi
    0.49
    Geplaatst
    0.48
     Chwiliwch
    0.47
    Activations Density 1.150%

    No Known Activations