© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8716
    Prev
    Next
    INDEX
    Explanations

    Swift protobuf code-related keywords such as optionals, try, Swift, and nil

    oai_token-act-pair · gemini-2.0-flash

    ?

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -1.62
    ?.
    -0.74
    '
    -0.71
    ?
    -0.66
    ’
    -0.65
    ?:
    -0.59
    ?"
    -0.59
    ?).
    -0.54
    ?”
    -0.53
    SPJ
    -0.51
    POSITIVE LOGITS
     aussit
    0.63
    Hec
    0.60
    contentLoaded
    0.56
     snoopy
    0.56
     Hec
    0.55
    oldown
    0.55
     engraçadas
    0.55
     Cigar
    0.54
     doulou
    0.54
     undec
    0.53
    Activations Density 3.694%

    No Known Activations