© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10033
    Prev
    Next
    INDEX
    Explanations

    words that add to a statement like a fact or opinion

    oai_token-act-pair · gemini-2.0-flash

    say "the [the]"

    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
    UrlResolution
    -0.89
    CppMethod
    -0.88
    WebVitals
    -0.84
    TemporalType
    -0.82
    SpringBootTest
    -0.82
     فريبيس
    -0.77
    MessageTagHelper
    -0.76
     صوتيه
    -0.76
    GEBURTSDATUM
    -0.76
    
    -0.75
    POSITIVE LOGITS
     the
    1.88
    the
    0.76
     την
    0.60
     poslední
    0.54
    The
    0.47
     το
    0.47
     οι
    0.47
    루
    0.45
    ofthe
    0.45
    tothe
    0.45
    Activations Density 4.233%

    No Known Activations