© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13071
    Prev
    Next
    INDEX
    Explanations

    instances of interactions, meetings, visiting, and contact.

    oai_token-act-pair · gemini-2.0-flash

    instances of meeting or connection

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

    meet

    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
     насеље
    -0.57
    новниш
    -0.52
     gynnwys
    -0.50
    ItemBackground
    -0.49
     đoạn
    -0.49
    Zeneca
    -0.48
     Odour
    -0.48
    geslacht
    -0.48
    ToScroll
    -0.47
    бливості
    -0.47
    POSITIVE LOGITS
     with
    0.71
    PDOException
    0.69
     protoimpl
    0.63
     up
    0.60
    риях
    0.54
     propOrder
    0.53
     CreateTagHelper
    0.52
    LookAnd
    0.51
     everybody
    0.49
     esternos
    0.48
    Activations Density 4.883%

    No Known Activations