© 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. 4320
    Prev
    Next
    INDEX
    Explanations

    code and words relating to visual boxes and fields

    oai_token-act-pair · gemini-2.0-flash

    box

    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
    Not in Any Lists

    No Comments

    Negative Logits
     box
    -3.09
    box
    -2.88
     Box
    -2.86
    Box
    -2.78
     boxes
    -2.67
     BOX
    -2.58
    BOX
    -2.53
     Boxes
    -2.53
    boxes
    -2.52
    Boxes
    -2.23
    POSITIVE LOGITS
     Início
    0.48
    hoeddwyd
    0.47
    EnableWeb
    0.47
    izeit
    0.47
    IUrlHelper
    0.46
    väg
    0.44
     antidesliz
    0.44
    []):
    0.44
     volna
    0.43
    ędziesz
    0.43
    Activations Density 3.219%

    No Known Activations