© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7136
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    <?

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     CURIAM
    -0.46
    dig
    -0.45
    WithIOException
    -0.44
     Baillargeon
    -0.43
     appelez
    -0.43
     لينك
    -0.41
     running
    -0.40
    ronesia
    -0.40
    elancer
    -0.40
    êng
    -0.39
    POSITIVE LOGITS
    mybatisplus
    0.72
    SuppressLint
    0.66
     purpoſe
    0.65
     Reſ
    0.63
     uſe
    0.63
    клопе
    0.60
     Efq
    0.59
    }>
    0.59
     ſta
    0.59
    ]}>
    0.57
    Activations Density 0.732%

    No Known Activations