© 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. 8322
    Prev
    Next
    INDEX
    Explanations

    language having to do with increasing or decreasing things.

    oai_token-act-pair · gemini-2.0-flash

    increase

    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
     Мексичка
    -0.57
    GenerationType
    -0.46
     '\\;'
    -0.45
    PTI
    -0.44
    Décès
    -0.44
     referenties
    -0.44
     Jove
    -0.44
     suns
    -0.43
     hudson
    -0.43
     Vikipedi
    -0.43
    POSITIVE LOGITS
     estekak
    0.63
    évaluateur
    0.62
    vanced
    0.61
    putstr
    0.58
    xnn
    0.58
    jsonwebtoken
    0.57
    RegressionTest
    0.56
     समीक्षाओं
    0.55
    ftant
    0.54
    ########.
    0.53
    Activations Density 0.383%

    No Known Activations