© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11409
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparison

    oai_token-act-pair · gemini-2.0-flash

    say "that"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     مشين
    -1.27
     tartalomajánló
    -1.19
     myſelf
    -1.16
     ―――――
    -1.05
     themſelves
    -1.05
     itſelf
    -1.05
    PerformLayout
    -1.03
    ſelves
    -1.02
    DockStyle
    -1.02
     Jefus
    -1.01
    POSITIVE LOGITS
     that
    1.75
    that
    0.94
     que
    0.75
     که
    0.73
     कि
    0.65
     bahwa
    0.65
     что
    0.63
     rằng
    0.63
     mà
    0.58
     That
    0.57
    Activations Density 9.008%

    No Known Activations