© 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. 4899
    Prev
    Next
    INDEX
    Explanations

    words related to progress in some area, like improving skills or knowledge.

    oai_token-act-pair · gemini-2.0-flash

    knowledge

    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
    wachsenen
    -0.54
    door
    -0.49
    Eksterne
    -0.49
    Välislingid
    -0.48
    ysz
    -0.46
    expandindo
    -0.45
    IVEREF
    -0.44
    MessageTagHelper
    -0.44
    aphone
    -0.44
    {{
    -0.44
    POSITIVE LOGITS
     knowledge
    1.02
    knowledge
    0.84
     Knowledge
    0.79
     znal
    0.79
    Knowledge
    0.78
     conocimiento
    0.74
     expertise
    0.73
     skills
    0.73
     connaissances
    0.73
     understanding
    0.70
    Activations Density 1.494%

    No Known Activations