© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6010
    Prev
    Next
    INDEX
    Explanations

    academic writing

    oai_token-act-pair · gemini-2.0-flash

    whole

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     itſelf
    -2.27
     Efq
    -2.23
     myſelf
    -2.16
     ſeveral
    -2.06
     Jefus
    -2.06
     Majefty
    -2.05
     Shakspeare
    -2.05
     pleaſure
    -1.99
     Monfieur
    -1.98
     Houſe
    -1.91
    POSITIVE LOGITS
     -
    1.05
     to
    1.03
     I
    1.03
     
    1.03
     (
    1.02
     for
    0.98
     in
    0.96
    <eos>
    0.95
     $
    0.95
     [
    0.95
    Activations Density 1.960%

    No Known Activations