© 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. 11192
    Prev
    Next
    INDEX
    Explanations

    quantifiers such as "some," "many," "much," and numbers.

    oai_token-act-pair · gemini-2.0-flash

    say "of"

    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
    Obrázky
    -0.67
    évaluateur
    -0.65
     pinulongan
    -0.60
    ⓧ
    -0.56
    lgari
    -0.56
     ujednoznacz
    -0.53
     BnF
    -0.50
    MemoryWarning
    -0.49
    ☸
    -0.48
     Wiktionnaire
    -0.47
    POSITIVE LOGITS
     of
    2.23
    of
    1.05
     của
    0.85
     Of
    0.82
    ของ
    0.81
    Of
    0.79
     OF
    0.74
    ofd
    0.71
     של
    0.71
    tof
    0.69
    Activations Density 3.904%

    No Known Activations