© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4087
    Prev
    Next
    INDEX
    Explanations

    the word "premium"

    oai_token-act-pair · gemini-2.0-flash

    premium

    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
     
    -1.70
     I
    -1.48
     (
    -1.47
     in
    -1.41
     a
    -1.39
     the
    -1.39
     [
    -1.36
    ↵↵
    -1.34
    <eos>
    -1.29
     and
    -1.28
    POSITIVE LOGITS
     myſelf
    3.19
     Efq
    3.11
     itſelf
    3.06
     Monfieur
    3.03
     Jefus
    2.92
     purpoſe
    2.89
     Majefty
    2.86
     Anſ
    2.83
     ſtate
    2.81
     pleaſure
    2.80
    Activations Density 2.661%

    No Known Activations