© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14557
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to groups of people and their actions

    oai_token-act-pair · gemini-2.0-flash

    various source excerpts

    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
    ----</
    -0.52
    GEBURTSDATUM
    -0.50
    styleable
    -0.49
     ModelRenderer
    -0.46
    ModelSerializer
    -0.46
     '\\;'
    -0.44
    GEBURTS
    -0.43
    racene
    -0.43
     ویکی‌پدیا
    -0.43
    __':
    -0.43
    POSITIVE LOGITS
    ThroughAttribute
    0.84
     campagna
    0.67
     виправивши
    0.60
    Chham
    0.58
     juridique
    0.58
     engraçadas
    0.55
    ///</
    0.55
     légère
    0.54
    fej
    0.54
     contemporaine
    0.53
    Activations Density 0.334%

    No Known Activations