© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4458
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to business and scientific settings.

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     double
    -0.49
    cheiden
    -0.47
     anteced
    -0.46
     splet
    -0.45
    Double
    -0.45
     Double
    -0.45
     dată
    -0.45
    Referències
    -0.44
    исленность
    -0.44
    awtextra
    -0.43
    POSITIVE LOGITS
    twimg
    0.69
    ciech
    0.55
    forRoot
    0.54
    ufc
    0.54
     Administrativna
    0.53
    +#+#
    0.52
     hiér
    0.52
    Référence
    0.51
    ginx
    0.51
    DIPSETTING
    0.51
    Activations Density 12.409%

    No Known Activations