© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13896
    Prev
    Next
    INDEX
    Explanations

    technical descriptions involving quantities and optimum conditions

    oai_token-act-pair · gemini-2.0-flash

    scientific data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bluff
    -0.42
    clu
    -0.42
     diversify
    -0.41
    pug
    -0.40
     mix
    -0.39
     exclusions
    -0.39
     diversified
    -0.38
    ร
    -0.38
     cả
    -0.37
    svn
    -0.37
    POSITIVE LOGITS
    AlterField
    0.78
     betweenstory
    0.77
     arşivlendi
    0.77
    ReusableCell
    0.73
     AssemblyCompany
    0.72
    uxxxx
    0.71
    tonode
    0.71
     surla
    0.70
     BaseActivity
    0.69
    IsContent
    0.68
    Activations Density 0.247%

    No Known Activations