© 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. 4922
    Prev
    Next
    INDEX
    Explanations

    text fragments with the characters "bu" appearing in them

    oai_token-act-pair · gemini-2.0-flash

    words starting with 'bu'

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

    bu

    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
    
    -0.46
    ber
    -0.42
    QUID
    -0.41
     ber
    -0.41
     Web
    -0.40
    WAIT
    -0.40
     مج
    -0.40
    ialog
    -0.40
    hau
    -0.40
    e
    -0.38
    POSITIVE LOGITS
     فريبيس
    1.03
    fjspx
    1.02
     насељу
    1.01
     betweenstory
    0.86
     otomatig
    0.84
     itſelf
    0.84
    InSection
    0.84
    MethodManager
    0.83
    fromnode
    0.83
     GenerationType
    0.83
    Activations Density 0.213%

    No Known Activations