© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10888
    Prev
    Next
    INDEX
    Explanations

    the phrases "a number", "a limited number", "a few," or "a small number."

    oai_token-act-pair · gemini-2.0-flash

    words beginning with 'a'

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

    foreign words

    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
     account
    -0.67
    thasone
    -0.66
     adult
    -0.60
    æa
    -0.59
    Ự
    -0.59
     article
    -0.58
    ÓS
    -0.58
     option
    -0.57
     auto
    -0.56
    eaway
    -0.56
    POSITIVE LOGITS
     protoimpl
    0.65
     quelqu
    0.57
     تضيفلها
    0.56
     nessun
    0.56
     nessuno
    0.55
     ognuno
    0.55
     qualcuno
    0.54
     suivants
    0.53
     emozioni
    0.53
     alguno
    0.52
    Activations Density 2.099%

    No Known Activations