© 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. 4109
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to cloth diapering

    oai_token-act-pair · gemini-2.0-flash

    beds and linens

    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
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.49
     Hickey
    -0.47
     cover
    -0.47
     ketat
    -0.45
     déroule
    -0.44
    帆
    -0.44
     Carpet
    -0.43
    Carpet
    -0.43
    cen
    -0.42
    ster
    -0.42
    POSITIVE LOGITS
     pleaſure
    0.77
    omeness
    0.70
     purpoſe
    0.69
     Efq
    0.67
     Monfieur
    0.64
    AnimationsModule
    0.63
    PhysRev
    0.63
     resourceCulture
    0.63
     reaſon
    0.62
    ModelAdmin
    0.62
    Activations Density 13.724%

    No Known Activations