© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3734
    Prev
    Next
    INDEX
    Explanations

    positive adjectives, adverbs like "rather," and qualitative descriptors generally.

    oai_token-act-pair · gemini-2.0-flash

    obscure or complex terms

    np_token-act-pair-logits · gpt-4o-mini

    Personal reflections

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    GeneratedCode
    -0.47
    [++
    -0.46
     Suppose
    -0.46
    onViewCreated
    -0.46
    出版年
    -0.45
     λε
    -0.44
     bullpen
    -0.43
    dailymail
    -0.42
    outSlope
    -0.42
    omer
    -0.41
    POSITIVE LOGITS
     rhestr
    0.64
    unate
    0.63
    scribers
    0.60
     TextInputType
    0.60
    kmäler
    0.59
     تانيه
    0.58
    //
    0.58
    WithIOException
    0.57
     précie
    0.57
    Cyfeiriadau
    0.57
    Activations Density 1.812%

    No Known Activations