© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13641
    Prev
    Next
    INDEX
    Explanations

    words and phrases describing reactions, positions, and defenses in legal, financial and physical contexts

    oai_token-act-pair · gemini-2.0-flash

    reactions and responses

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ContentAsync
    -0.74
    AddTagHelper
    -0.57
    conceito
    -0.55
     jöv
    -0.54
     japonesa
    -0.53
    WebServlet
    -0.52
    anuts
    -0.51
     TextEditing
    -0.50
     TextInputType
    -0.50
     nemlig
    -0.50
    POSITIVE LOGITS
    Abitanti
    0.50
     समीक्षक
    0.49
    atisfied
    0.49
    Facades
    0.48
     responses
    0.47
    ylen
    0.47
     حاج
    0.46
    OrNil
    0.45
    forRoot
    0.45
     RESPOND
    0.44
    Activations Density 2.418%

    No Known Activations