© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11945
    Prev
    Next
    INDEX
    Explanations

    words ending in "nt", "ence", "ism", "ity", "ee", and words starting with "trans", "inf", "anti", and "per"

    oai_token-act-pair · gemini-2.0-flash

    unusual text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    nent
    -0.81
    ItemBackground
    -0.81
    nem
    -0.79
    AnchorStyles
    -0.76
    mn
    -0.76
     NEM
    -0.76
    SceneManagement
    -0.76
    nm
    -0.75
     IMC
    -0.75
    RectangleBorder
    -0.74
    POSITIVE LOGITS
    ytale
    0.55
    Népesség
    0.50
     Reproduce
    0.49
    \}_{
    0.48
    liwości
    0.47
     letech
    0.47
    Kariera
    0.45
     sítio
    0.45
     kasarigan
    0.45
    ちゃった
    0.44
    Activations Density 4.173%

    No Known Activations