© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15336
    Prev
    Next
    INDEX
    Explanations

    dates, times, anniversaries, and other temporal references

    oai_token-act-pair · gemini-2.0-flash

    might and may

    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
    PhysRevLett
    -0.48
    ILS
    -0.47
    andır
    -0.44
     Lune
    -0.44
     Bili
    -0.43
    SBATCH
    -0.43
    ouden
    -0.43
    ils
    -0.43
     selv
    -0.42
     Pathology
    -0.41
    POSITIVE LOGITS
     might
    2.28
    might
    2.11
     Might
    2.08
    Might
    2.06
     may
    1.98
    may
    1.88
    May
    1.80
     May
    1.77
     MIGHT
    1.70
     MAY
    1.65
    Activations Density 1.723%

    No Known Activations