© 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. 9883
    Prev
    Next
    INDEX
    Explanations

    text that contains a statement, followed by evidence or an example

    oai_token-act-pair · gemini-2.0-flash

    say "instance/example"

    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
     instances
    -2.00
     instance
    -1.98
     Instance
    -1.85
    instance
    -1.84
    Instance
    -1.81
     Instances
    -1.80
     cases
    -1.75
    Instances
    -1.68
    instances
    -1.66
     Cases
    -1.59
    POSITIVE LOGITS
     kasarigan
    0.77
     AssemblyCulture
    0.66
     الحره
    0.64
    tagHelperRunner
    0.63
     himo
    0.62
     المعيارى
    0.60
    AnchorStyles
    0.60
    üyada
    0.59
     صوتيه
    0.59
     مرئيه
    0.58
    Activations Density 1.619%

    No Known Activations