© 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. 4200
    Prev
    Next
    INDEX
    Explanations

    phrases that involve "sake" or words related to "shocking" things

    oai_token-act-pair · gemini-2.0-flash

    sake

    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
    ArrowToggle
    -0.54
     bArr
    -0.54
    verwijspagina
    -0.48
    IntoConstraints
    -0.46
     XNUMX
    -0.44
    WebServlet
    -0.44
    ImageContext
    -0.44
    aarrggbb
    -0.44
     تضيفلها
    -0.43
     sowas
    -0.43
    POSITIVE LOGITS
     sake
    1.56
     Sake
    1.09
    ake
    0.85
    AddTagHelper
    0.82
    akes
    0.69
    aken
    0.62
    缘
    0.61
    zake
    0.59
     FOR
    0.59
     for
    0.59
    Activations Density 0.407%

    No Known Activations