© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 2975
    Prev
    Next
    INDEX
    Explanations

    the word "cleaning"

    oai_token-act-pair · gemini-2.0-flash

    cleaning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     purpoſe
    -1.28
     myſelf
    -1.25
     themſelves
    -1.18
     ſtate
    -1.14
     ſmall
    -1.10
     Theſe
    -1.09
     pleaſure
    -1.08
     poffible
    -1.07
     houſe
    -1.05
     Majefty
    -1.05
    POSITIVE LOGITS
    IUrlHelper
    0.73
    ibouti
    0.69
    Facades
    0.69
    jsonPath
    0.69
    rillation
    0.67
    LEncoder
    0.66
    oneofs
    0.65
    verwijspagina
    0.65
    ymce
    0.63
    rings
    0.62
    Activations Density 1.771%

    No Known Activations