© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7957
    Prev
    Next
    INDEX
    Explanations

    technical language related to protocols and standards that govern mobile stations on wireless networks.

    oai_token-act-pair · gemini-2.0-flash

    words related to sending

    np_token-act-pair-logits · gpt-4o-mini

    sending

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Built
    -0.48
    MigrationBuilder
    -0.47
     médicale
    -0.46
     finder
    -0.44
    built
    -0.44
    Built
    -0.43
    TagHelper
    -0.42
     Grows
    -0.42
     hạn
    -0.41
     bygger
    -0.41
    POSITIVE LOGITS
     send
    1.34
     sending
    1.34
     sends
    1.22
     issuing
    1.21
    send
    1.20
    sending
    1.20
    Sending
    1.17
    Send
    1.16
     Sending
    1.16
     Send
    1.13
    Activations Density 4.017%

    No Known Activations