© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15436
    Prev
    Next
    INDEX
    Explanations

    numerical data, especially in tables and formulas

    oai_token-act-pair · gemini-2.0-flash

    Special characters

    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
    ?,?,
    -0.66
    Autoritní
    -0.58
    (_,
    -0.57
    Datuak
    -0.56
     للاسماء
    -0.55
    rieve
    -0.52
    '))
    -0.52
     كومونز
    -0.51
    }>;
    -0.51
    omla
    -0.51
    POSITIVE LOGITS
    AndFlush
    0.63
     CountDown
    0.57
     تضيفلها
    0.56
     tanong
    0.55
    destroyAll
    0.52
    igshid
    0.50
     &___
    0.50
    FirstResponder
    0.49
    SpringBootTest
    0.49
     crossorigin
    0.48
    Activations Density 1.116%

    No Known Activations