© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6396
    Prev
    Next
    INDEX
    Explanations

    the word "oral" or the term "portfolio"

    oai_token-act-pair · gemini-2.0-flash

    oral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    …
    -0.67
    kla
    -0.60
     …
    -0.58
    The
    -0.57
     
    -0.57
    _
    -0.56
     intent
    -0.56
    org
    -0.56
    for
    -0.56
    pr
    -0.55
    POSITIVE LOGITS
    Jeografia
    1.16
    BufferException
    1.16
     Roskov
    1.13
    
    1.09
    mybatisplus
    1.08
     snippetHide
    1.07
     AssemblyTitle
    1.02
     Normdatei
    1.02
     disambiguazione
    1.01
    InjectAttribute
    1.00
    Activations Density 0.579%

    No Known Activations