© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15966
    Prev
    Next
    INDEX
    Explanations

    words that are frequently used, such as articles, prepositions, and pronouns

    oai_token-act-pair · gemini-2.0-flash

    personal stories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    AndEndTag
    -0.90
     kubernetes
    -0.87
     IAEA
    -0.83
     NBS
    -0.81
     EEU
    -0.80
    AnimationsModule
    -0.79
     OLS
    -0.78
     IHC
    -0.77
     AIAA
    -0.77
    MethodManager
    -0.77
    POSITIVE LOGITS
    ことができました
    0.36
    Read
    0.32
    TagMode
    0.29
     touch
    0.28
    ようになりました
    0.27
    mě
    0.26
    rač
    0.26
     poste
    0.26
     ве
    0.26
    Iden
    0.25
    Activations Density 40.179%

    No Known Activations