© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 14053
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and values, particularly those involving fractions, limits, and negative signs

    oai_token-act-pair · gemini-2.0-flash

    math, physics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ✭✭
    -0.73
    GEBURTS
    -0.72
    adaptiveStyles
    -0.71
    UserScript
    -0.70
    WebElementEntity
    -0.69
    पया
    -0.68
    ंदीखरीदारी
    -0.67
    دانشنامهٔ
    -0.66
     فريبيس
    -0.65
    IVEREF
    -0.64
    POSITIVE LOGITS
    IBOutlet
    0.45
    execSQL
    0.41
    exao
    0.40
    endforeach
    0.39
    monton
    0.38
     Cronin
    0.36
     canadien
    0.36
     dags
    0.36
     tố
    0.35
    schirm
    0.34
    Activations Density 2.751%

    No Known Activations