© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3913
    Prev
    Next
    INDEX
    Explanations

    biblical references, particularly measurements and ingredients

    oai_token-act-pair · gemini-2.0-flash

    random text and math

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    GIVEREF
    -0.61
     Савезне
    -0.57
    पया
    -0.56
    uxxxx
    -0.52
     Minder
    -0.52
    WriteTagHelper
    -0.52
     समीक्षक
    -0.52
     AssemblyCompany
    -0.51
    timately
    -0.50
     sekal
    -0.50
    POSITIVE LOGITS
     الحره
    0.69
     OnInit
    0.61
    GraphicsUnit
    0.55
    }{*}{}
    0.53
    ʊ
    0.48
     emer
    0.48
    +#+#
    0.47
    stdc
    0.47
    umburg
    0.47
    tiftung
    0.46
    Activations Density 1.670%

    No Known Activations