© 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. 12949
    Prev
    Next
    INDEX
    Explanations

    technical writing and numbers

    oai_token-act-pair · gemini-2.0-flash

    technical data and separators

    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
     has
    -1.78
     have
    -1.68
     had
    -1.67
     are
    -1.62
     was
    -1.61
     is
    -1.54
     were
    -1.54
     will
    -1.52
     gets
    -1.49
     could
    -1.48
    POSITIVE LOGITS
     fubject
    0.54
     själ
    0.51
     ſtate
    0.50
    +:+
    0.50
    Artik
    0.49
    mybatisplus
    0.48
     quelcon
    0.48
     Diſ
    0.47
     associative
    0.47
     arbejds
    0.47
    Activations Density 39.529%

    No Known Activations