© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7870
    Prev
    Next
    INDEX
    Explanations

    words related to superlative concepts, and also the syllable "ne"

    oai_token-act-pair · gemini-2.0-flash

    ever

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    npy
    -0.48
    diki
    -0.46
     handel
    -0.46
    carbox
    -0.43
    TextAlign
    -0.43
    כא
    -0.43
     BENE
    -0.41
     Hirsch
    -0.41
    emm
    -0.41
    liders
    -0.40
    POSITIVE LOGITS
    +#+#
    0.84
    RenderAtEndOf
    0.78
    LEncoder
    0.75
    ViewImports
    0.74
    ruptedException
    0.73
     referenties
    0.73
    InstanceState
    0.72
    GetBytes
    0.71
    AddTagHelper
    0.71
    клопе
    0.70
    Activations Density 1.257%

    No Known Activations