© 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. 5233
    Prev
    Next
    INDEX
    Explanations

    words associated with the presence of people, their emotions, and body parts

    oai_token-act-pair · gemini-2.0-flash

    smiling

    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
    脚注の使い方
    -0.64
    ագրություններ
    -0.63
    Архівовано
    -0.62
    ParallelGroup
    -0.61
    MigrationBuilder
    -0.57
    /**
    -0.55
    TagMode
    -0.54
    躇
    -0.54
    Билгалдахарш
    -0.51
    AndEndTag
    -0.51
    POSITIVE LOGITS
    Personensuche
    0.75
     newBuilder
    0.68
     under
    0.67
     otomatig
    0.58
     Under
    0.57
    gação
    0.57
     كورة
    0.57
     valid
    0.56
     UNDER
    0.56
    esez
    0.55
    Activations Density 10.825%

    No Known Activations