© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15540
    Prev
    Next
    INDEX
    Explanations

    words describing corporations and government agencies

    oai_token-act-pair · gemini-2.0-flash

    private

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    :✨
    -0.71
     épar
    -0.70
     vettor
    -0.69
     duquel
    -0.68
    طلحات
    -0.67
     geométrico
    -0.67
     tombé
    -0.67
     suprême
    -0.66
     élector
    -0.66
     vectorielle
    -0.65
    POSITIVE LOGITS
     private
    0.86
    private
    0.76
     Private
    0.73
    Private
    0.66
    PRIVATE
    0.60
    priv
    0.59
     Privat
    0.57
     proprietary
    0.57
     privat
    0.56
     част
    0.56
    Activations Density 2.453%

    No Known Activations