© 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. 11170
    Prev
    Next
    INDEX
    Explanations

    javascript unit tests: it finds the characters that frame a test case definition

    oai_token-act-pair · gemini-2.0-flash

    parentheses

    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
     "
    -0.50
    ↵
    -0.47
    Off
    -0.47
    bon
    -0.46
    OS
    -0.45
    springframework
    -0.45
    ver
    -0.45
    ate
    -0.44
    ta
    -0.44
     
    -0.44
    POSITIVE LOGITS
    tvguidetime
    0.91
     '\\;'
    0.91
     Roskov
    0.89
     esternos
    0.88
     ModelExpression
    0.85
     وتسجيلات
    0.82
    AndEndTag
    0.80
    Jegyzetek
    0.79
    StoryboardSegue
    0.79
    Bronnen
    0.78
    Activations Density 0.583%

    No Known Activations