© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7331
    Prev
    Next
    INDEX
    Explanations

    connecting words or phrases plus words related to the word "sleep"

    oai_token-act-pair · gemini-2.0-flash

    forms of "a"

    np_max-act-logits · gemini-2.0-flash

    indefinite articles (a)

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     AttributeSet
    -0.58
    OGND
    -0.57
     الاطلاع
    -0.52
    poptosis
    -0.50
    kloped
    -0.49
    тистика
    -0.46
    webElement
    -0.46
     propOrder
    -0.46
    AnimationsModule
    -0.46
    __":
    -0.45
    POSITIVE LOGITS
     a
    3.00
    a
    1.25
     eine
    0.86
     ein
    0.84
    ａ
    0.82
     một
    0.82
     sebuah
    0.81
     einen
    0.81
     Sebuah
    0.81
     seorang
    0.79
    Activations Density 16.214%

    No Known Activations