© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6741
    Prev
    Next
    INDEX
    Explanations

    different things like the word nerve within a medical context, database keys, taxes, journeying and words related to creating and loading.

    oai_token-act-pair · gemini-2.0-flash

    code, medicine, tax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -0.89
     Monfieur
    -0.80
     Jefus
    -0.77
     myſelf
    -0.75
    GEBURTSDATUM
    -0.72
     purpoſe
    -0.71
     itſelf
    -0.71
     Reſ
    -0.69
     reaſon
    -0.69
     RSSSF
    -0.67
    POSITIVE LOGITS
    idue
    0.52
     سكانية
    0.49
    AddTagHelper
    0.47
    elum
    0.46
     filha
    0.46
    ikis
    0.44
    FieldOffset
    0.44
    everyone
    0.44
    elan
    0.44
     Cal
    0.43
    Activations Density 0.997%

    No Known Activations