© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3720
    Prev
    Next
    INDEX
    Explanations

    articles "a" and "an" followed by adjectives

    oai_token-act-pair · gemini-2.0-flash

    phrases with significant adjectives

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

    a

    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
     externi
    -0.55
    merzen
    -0.47
    visející
    -0.46
     Frankel
    -0.45
    ÍS
    -0.44
    стероид
    -0.44
     apunta
    -0.44
    atillo
    -0.43
    rungsseite
    -0.43
     Hew
    -0.43
    POSITIVE LOGITS
     مشين
    0.69
     ExecuteAsync
    0.64
    SequentialGroup
    0.53
    InstrumentedTest
    0.53
    HtmlAttribute
    0.51
     '\\;'
    0.51
    ToAction
    0.50
    рные
    0.50
     <<<<<<<<<<<<<<
    0.50
    '}),
    0.49
    Activations Density 0.515%

    No Known Activations