© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5603
    Prev
    Next
    INDEX
    Explanations

    words that modify nouns in questions or conditional statements

    oai_token-act-pair · gemini-2.0-flash

    any

    np_max-act-logits · gemini-2.0-flash
    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
     the
    -0.79
     an
    -0.71
     a
    -0.69
     it
    -0.66
     to
    -0.59
     these
    -0.59
    idhi
    -0.57
    ifilm
    -0.57
    -};
    -0.55
    ANCY
    -0.54
    POSITIVE LOGITS
     of
    1.10
    of
    0.69
     medlemmer
    0.57
     propOrder
    0.57
     của
    0.56
    ของ
    0.52
     toekomst
    0.51
     cavallo
    0.51
     unul
    0.50
     vectorielle
    0.49
    Activations Density 12.101%

    No Known Activations