© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8790
    Prev
    Next
    INDEX
    Explanations

    the word "okay" and its variants

    oai_token-act-pair · gemini-2.0-flash

    specific programming keywords or terms

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

    ok

    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
    <bos>
    -0.43
    рих
    -0.42
    shaw
    -0.40
     g
    -0.38
     quiet
    -0.37
     разви
    -0.37
    strup
    -0.37
    धिक
    -0.37
    leg
    -0.36
    fa
    -0.36
    POSITIVE LOGITS
     MainAxisSize
    0.84
    ArrowToggle
    0.82
    __":
    0.81
     Roskov
    0.80
     NSCoder
    0.74
    InjectAttribute
    0.74
     ویکی‌پدیای
    0.73
     AppCompatTheme
    0.69
    ViewStyle
    0.69
    AutoScale
    0.67
    Activations Density 1.879%

    No Known Activations