© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12813
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to forests and conservation

    oai_token-act-pair · gemini-2.0-flash

    terms related to trees and forests

    np_token-act-pair-logits · gpt-4o-mini

    trees and forests

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    awtextra
    -0.68
    ThroughAttribute
    -0.63
     initComponents
    -0.60
    lgari
    -0.60
    AddHtmlAttribute
    -0.59
    SharedCtor
    -0.58
     disulfide
    -0.56
    Numerology
    -0.53
    findpost
    -0.53
    ValueGeneration
    -0.52
    POSITIVE LOGITS
     trees
    1.27
     tree
    1.23
     forest
    1.16
     woods
    1.10
     Trees
    1.04
     Forest
    1.03
     forests
    1.03
     oak
    1.02
     wood
    1.01
    tree
    1.01
    Activations Density 1.984%

    No Known Activations