© 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. 12927
    Prev
    Next
    INDEX
    Explanations

    the word "consistent", sometimes near words indicating negativity

    oai_token-act-pair · gemini-2.0-flash

    consistent

    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
     
    -1.09
     I
    -1.07
     It
    -0.90
     We
    -0.88
     [
    -0.86
     A
    -0.84
    <eos>
    -0.83
     The
    -0.82
     (
    -0.80
     L
    -0.80
    POSITIVE LOGITS
     Efq
    2.09
     myſelf
    1.91
     Majefty
    1.87
     iſt
    1.86
     auffi
    1.84
     Monfieur
    1.80
    ſelf
    1.80
     Reſ
    1.80
     itſelf
    1.79
     raiſ
    1.76
    Activations Density 1.481%

    No Known Activations