© 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. 4747
    Prev
    Next
    INDEX
    Explanations

    code and programming concepts related to specifying dates and times

    oai_token-act-pair · gemini-2.0-flash

    Colon/Quotation marks

    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
    AndEndTag
    -0.79
    Personendaten
    -0.78
    ValueGenerated
    -0.78
    RenderAtEndOf
    -0.72
    ContentAsync
    -0.71
    intios
    -0.71
     '\\;'
    -0.69
     <<<<<<<<<<<<<<
    -0.69
     disambiguazione
    -0.68
    Morfologia
    -0.67
    POSITIVE LOGITS
    heide
    0.47
    ortun
    0.46
     liné
    0.44
     /*
    0.44
    Tog
    0.43
    itex
    0.43
    PRNewswire
    0.42
     éti
    0.42
    that
    0.42
    setContentType
    0.42
    Activations Density 8.534%

    No Known Activations