© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6207
    Prev
    Next
    INDEX
    Explanations

    the character "@" at the beginning of a token, and variables in PHP that start with "$_". It also finds the word "missing".

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Monfieur
    -1.53
     Efq
    -1.46
     Jefus
    -1.38
     Majefty
    -1.38
     Eſ
    -1.37
     myſelf
    -1.32
     houſe
    -1.30
     whoſe
    -1.30
     pleaſure
    -1.30
     Diſ
    -1.29
    POSITIVE LOGITS
     
    0.90
     I
    0.84
     (
    0.71
     La
    0.69
    <eos>
    0.67
     P
    0.67
     @
    0.64
     the
    0.60
     L
    0.60
     Mar
    0.60
    Activations Density 0.923%

    No Known Activations