© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6022
    Prev
    Next
    INDEX
    Explanations

    verbs in the English language

    oai_token-act-pair · gemini-2.0-flash

    say "the"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Pyx
    -0.58
    ❋
    -0.50
    ########.
    -0.47
    mitas
    -0.46
     deles
    -0.46
    بوابة
    -0.45
    einem
    -0.45
     ویکی‌پدیای
    -0.44
    netinet
    -0.44
     tartalomajánló
    -0.44
    POSITIVE LOGITS
     the
    2.08
     mergeFrom
    0.85
    SourceChecksum
    0.81
    the
    0.66
     ویکی‌پدی
    0.63
    RegressionTest
    0.61
     την
    0.57
    private
    0.57
    CloseOperation
    0.56
     året
    0.55
    Activations Density 4.070%

    No Known Activations