© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13260
    Prev
    Next
    INDEX
    Explanations

    variations of the word "realise" and words associated with potential, or the future

    oai_token-act-pair · gemini-2.0-flash

    realize

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Houſe
    -1.22
     Monfieur
    -1.19
     Reſ
    -1.19
     houſe
    -1.13
     Majefty
    -1.12
     itſelf
    -1.12
     Eſ
    -1.09
     Conſ
    -1.09
     iſt
    -1.06
    ſelves
    -1.06
    POSITIVE LOGITS
    OGND
    0.84
     Paglinawan
    0.71
     the
    0.69
    Autoritní
    0.65
     and
    0.65
     Numerade
    0.63
    tagHelperRunner
    0.62
    ,
    0.62
     -
    0.62
    Personensuche
    0.61
    Activations Density 2.531%

    No Known Activations