© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 458
    Prev
    Next
    INDEX
    Explanations

    expressions related to feeling supported or empowered despite hardship

    oai_token-act-pair · gemini-2.0-flash

    talking, chat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     nahilalakip
    -0.93
     Monfieur
    -0.84
     myſelf
    -0.84
     purpoſe
    -0.83
    ⓧ
    -0.82
     EconPapers
    -0.82
    IGraphics
    -0.82
    UserScript
    -0.80
     becauſe
    -0.78
     pleaſure
    -0.78
    POSITIVE LOGITS
    Chat
    0.40
     chat
    0.40
    vud
    0.40
    ğaz
    0.39
    -
    0.38
     atenção
    0.37
     previsão
    0.36
    Talk
    0.36
    chata
    0.36
     talk
    0.36
    Activations Density 1.364%

    No Known Activations