© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14132
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    he

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    :]:
    -0.54
     كومونز
    -0.51
    RTN
    -0.49
    mergeFrom
    -0.48
     الرخصة
    -0.48
     newBuilder
    -0.48
    aneously
    -0.48
    OutputType
    -0.47
    شوف
    -0.46
    dientemente
    -0.46
    POSITIVE LOGITS
     uſed
    0.70
     Préférences
    0.66
    SourceChecksum
    0.64
     houſe
    0.59
    lidays
    0.58
    ########.
    0.57
     propOrder
    0.56
     ſhe
    0.55
     ſte
    0.55
     désolés
    0.55
    Activations Density 5.114%

    No Known Activations