© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12199
    Prev
    Next
    INDEX
    Explanations

    words related to personal opinion, disagreement or feelings like dislike or honesty as well as some profanity

    oai_token-act-pair · gemini-2.0-flash

    curse words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Personensuche
    -0.77
    FUCK
    -0.71
    postsleuth
    -0.68
    tldr
    -0.67
     unknownFields
    -0.67
     fucking
    -0.67
    曖昧さ回避
    -0.66
     Wtf
    -0.66
    ValueStyle
    -0.65
     autorytatywna
    -0.62
    POSITIVE LOGITS
     idéia
    0.62
     läßt
    0.54
     becauſe
    0.53
     tranſ
    0.53
    Aholisi
    0.52
     fubject
    0.52
     Sandi
    0.51
    ㄋ
    0.50
     Dostupné
    0.50
     Inscrivez
    0.50
    Activations Density 11.285%

    No Known Activations