© 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. 14660
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue combined with names and titles

    oai_token-act-pair · gemini-2.0-flash

    historical/classical contexts

    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
     '{@
    -0.66
    InSection
    -0.66
    tagHelperRunner
    -0.65
    liferay
    -0.65
    expandindo
    -0.64
     IndexPath
    -0.63
     MaterialApp
    -0.63
    AndEndTag
    -0.61
    Gambas
    -0.60
    testify
    -0.58
    POSITIVE LOGITS
    UserScript
    0.58
    Източници
    0.46
     antworten
    0.44
     kasarigan
    0.41
     Meksiku
    0.41
    rural
    0.39
    جغرافيا
    0.39
     De
    0.39
     con
    0.38
    Derbyniad
    0.38
    Activations Density 0.658%

    No Known Activations