© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14215
    Prev
    Next
    INDEX
    Explanations

    references to theories, studies, statistics, opinions, and conclusions

    oai_token-act-pair · 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
     misses
    -0.78
     Misses
    -0.75
     soient
    -0.69
     waits
    -0.68
     mixes
    -0.67
     drives
    -0.66
     crosses
    -0.65
     runs
    -0.65
     escapes
    -0.63
    Keeps
    -0.63
    POSITIVE LOGITS
     apply
    0.84
     offer
    0.82
     respond
    0.80
     marry
    0.79
     carry
    0.78
     turn
    0.77
     undergo
    0.77
     undertake
    0.77
     convert
    0.77
     expose
    0.77
    Activations Density 3.573%

    No Known Activations