© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15548
    Prev
    Next
    INDEX
    Explanations

    words/phrases about future availability or upcoming events.

    oai_token-act-pair · gemini-2.0-flash

    words indicating upcoming events or releases

    np_token-act-pair-logits · gpt-4o-mini

    soon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    存于互联网档案馆
    -0.56
    AndEndTag
    -0.47
     "..\..\
    -0.47
     HasFactory
    -0.47
     "..\..\..\
    -0.47
    期刊论文
    -0.46
    دانشنامهٔ
    -0.46
     persil
    -0.45
     vigueur
    -0.44
    >{@
    -0.44
    POSITIVE LOGITS
     soon
    3.39
    Soon
    2.89
     Soon
    2.88
    soon
    2.88
     SOON
    2.39
     bientôt
    1.95
     snart
    1.89
     foon
    1.87
     shortly
    1.83
     segera
    1.51
    Activations Density 2.489%

    No Known Activations