© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12823
    Prev
    Next
    INDEX
    Explanations

    technical terms in chemistry or biology involving multiple syllables, particularly polymers and nanoparticles.

    oai_token-act-pair · gemini-2.0-flash

    say "nanoparticles"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    AddTagHelper
    -0.71
     nahilalakip
    -0.69
    MigrationBuilder
    -0.66
    awtextra
    -0.65
    -------------</
    -0.64
    appspot
    -0.59
    $_['
    -0.58
    jectures
    -0.58
     defaultstate
    -0.57
    ThroughAttribute
    -0.57
    POSITIVE LOGITS
     preparations
    0.52
     Niet
    0.49
     reinforced
    0.48
     foams
    0.45
     BigInt
    0.44
     fura
    0.43
     Pyrenees
    0.43
    migrations
    0.43
    Portály
    0.43
     חיצוניים
    0.42
    Activations Density 7.202%

    No Known Activations