© 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. 13145
    Prev
    Next
    INDEX
    Explanations

    statistical analysis terms and relative comparisons.

    oai_token-act-pair · gemini-2.0-flash

    small quantities

    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
     (>
    -0.70
     more
    -0.69
    ≥
    -0.68
     viac
    -0.67
     exceeds
    -0.66
     více
    -0.66
    超过
    -0.65
     >
    -0.65
    more
    -0.64
     longest
    -0.63
    POSITIVE LOGITS
     little
    0.81
    little
    0.78
    LITTLE
    0.73
     LITTLE
    0.73
    ess
    0.71
     few
    0.69
    few
    0.66
     Few
    0.65
    Few
    0.64
    Little
    0.62
    Activations Density 3.348%

    No Known Activations