© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12475
    Prev
    Next
    INDEX
    Explanations

    C code related to command line arguments

    oai_token-act-pair · gemini-2.0-flash

    argc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     виправивши
    -0.91
    تقاوى
    -0.84
     >=",
    -0.77
     utafitiHapana
    -0.74
     kaarangay
    -0.67
    __*/
    -0.66
    ClientSize
    -0.65
    PerformLayout
    -0.64
     nahilalakip
    -0.63
    ISupport
    -0.62
    POSITIVE LOGITS
    familie
    0.45
     consigo
    0.45
    عاون
    0.43
     برانيه
    0.40
    HttpPut
    0.40
    </blockquote>
    0.40
    atchi
    0.39
     جات
    0.38
     Stacks
    0.37
     picked
    0.36
    Activations Density 1.181%

    No Known Activations