© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4272
    Prev
    Next
    INDEX
    Explanations

    instances of people expressing their feelings or opinions about public matters

    oai_token-act-pair · gemini-2.0-flash

    I or we

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    StoreMessageInfo
    -0.60
     numerus
    -0.57
    WebServlet
    -0.55
    MockBean
    -0.50
    writeFieldEnd
    -0.50
    Personensuche
    -0.49
     Holger
    -0.49
     JADX
    -0.49
    glLoadIdentity
    -0.47
     dars
    -0.47
    POSITIVE LOGITS
     pewno
    0.66
    nościo
    0.65
    WillAppear
    0.53
     wish
    0.53
     know
    0.52
     године
    0.52
     note
    0.51
     hope
    0.51
     wished
    0.51
     ),
    0.51
    Activations Density 1.753%

    No Known Activations