© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15355
    Prev
    Next
    INDEX
    Explanations

    words, phrases and patterns used to direct the viewers attention.

    oai_token-act-pair · gemini-2.0-flash

    see also, here's

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     оригіналу
    -0.75
     OMITBAD
    -0.48
     medži
    -0.44
     démo
    -0.42
     dė
    -0.42
     diversité
    -0.42
    стви
    -0.41
     nourrir
    -0.41
    Repeating
    -0.41
     helyez
    -0.41
    POSITIVE LOGITS
    ftagPool
    0.73
    Tembelea
    0.71
     Мексичка
    0.70
    __':
    0.69
     BorderRadius
    0.69
     StatefulWidget
    0.69
    __":
    0.68
     ModelExpression
    0.66
    paksa
    0.64
     дописавши
    0.64
    Activations Density 9.565%

    No Known Activations