© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13153
    Prev
    Next
    INDEX
    Explanations

    lines of code importing Android libraries and Google's Gson library

    oai_token-act-pair · gemini-2.0-flash

    android

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ganggu
    -0.34
     albicans
    -0.34
    pulsar
    -0.34
    rena
    -0.33
    rel
    -0.33
     intre
    -0.33
     donc
    -0.32
    raw
    -0.32
    </code>
    -0.32
    さわ
    -0.32
    POSITIVE LOGITS
     समीक्षाओं
    0.86
    Vidite
    0.82
    脚注の使い方
    0.77
     Савезне
    0.76
     <>",
    0.73
     Monfieur
    0.73
     }}"></
    0.72
     betweenstory
    0.70
     estimés
    0.69
    bewerken
    0.65
    Activations Density 0.507%

    No Known Activations