© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9309
    Prev
    Next
    INDEX
    Explanations

    mentions of filters

    oai_token-act-pair · gemini-2.0-flash

    filter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    AnchorStyles
    -0.73
    awtextra
    -0.56
    . 
    -0.56
     _("
    -0.56
     destinées
    -0.54
    ῖ
    -0.53
     neben
    -0.52
     filter
    -0.52
     ligero
    -0.51
    CardBody
    -0.51
    POSITIVE LOGITS
    Хьажоргаш
    0.73
    ніципа
    0.69
     Meksiku
    0.67
    ⓧ
    0.67
    blic
    0.67
    trico
    0.67
     Cel
    0.66
    lorette
    0.65
    SqlClient
    0.63
    าสตร์
    0.63
    Activations Density 0.585%

    No Known Activations