© 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. 15204
    Prev
    Next
    INDEX
    Explanations

    German words or phrases within a scientific context.

    oai_token-act-pair · gemini-2.0-flash

    code, math, German

    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
    Not in Any Lists

    No Comments

    Negative Logits
     aventure
    -0.40
    opsis
    -0.40
    logeny
    -0.39
    Personendaten
    -0.38
     citta
    -0.37
     connaissance
    -0.37
     Wikiseite
    -0.37
     connaissances
    -0.36
    illoma
    -0.36
     bulunabilir
    -0.36
    POSITIVE LOGITS
    mybatisplus
    0.87
     المعيارى
    0.82
    ConstraintMaker
    0.81
    contentLoaded
    0.59
    InSection
    0.58
    Rei
    0.58
    +:+
    0.57
    PreferredItem
    0.57
     يتيمه
    0.56
     paja
    0.56
    Activations Density 5.182%

    No Known Activations