© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 721
    Prev
    Next
    INDEX
    Explanations

    words that are stop words or used very commonly

    oai_token-act-pair · gemini-2.0-flash

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    <?
    -0.56
     []:
    -0.46
    
    -0.45
     <-
    -0.42
    #!/
    -0.42
    KEEP
    -0.42
    awtextra
    -0.42
    Keep
    -0.41
     keep
    -0.39
    /*
    -0.38
    POSITIVE LOGITS
     Efq
    0.73
    uxxxx
    0.69
     NDEBUG
    0.68
     Administrativna
    0.65
     Kün
    0.64
     ſeveral
    0.63
     returned
    0.63
     AssemblyVersion
    0.63
     jsPsych
    0.62
    migrationBuilder
    0.61
    Activations Density 4.043%

    No Known Activations