© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13250
    Prev
    Next
    INDEX
    Explanations

    common function words such as "a", "the", "of", and "to" occurring in a text

    oai_token-act-pair · gemini-2.0-flash

    research papers

    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
     Subsequent
    -0.60
     Actual
    -0.59
    Actual
    -0.59
    actual
    -0.56
     singola
    -0.55
     actualidad
    -0.54
    ranean
    -0.53
     normaux
    -0.53
    eseorang
    -0.52
    ACTUAL
    -0.52
    POSITIVE LOGITS
     known
    0.76
     announced
    0.69
     reported
    0.69
     published
    0.67
     observed
    0.65
    WindowConstants
    0.64
    StoryboardSegue
    0.63
     stated
    0.62
     Known
    0.62
     declared
    0.60
    Activations Density 16.668%

    No Known Activations