© 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. 8068
    Prev
    Next
    INDEX
    Explanations

    the color brown

    oai_token-act-pair · gemini-2.0-flash

    brown

    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
     Cæsar
    -0.84
     useStyles
    -0.81
     giapp
    -0.79
     photolibrary
    -0.77
     subgoal
    -0.77
     pacchetto
    -0.75
     inglesa
    -0.75
     acceptez
    -0.73
     Mahomet
    -0.72
     eletrônico
    -0.71
    POSITIVE LOGITS
    ENTLY
    0.72
     now
    0.68
    ÉM
    0.67
     alia
    0.67
    OfBirth
    0.66
    Numerade
    0.65
     full
    0.65
     auto
    0.65
     all
    0.65
     not
    0.64
    Activations Density 2.068%

    No Known Activations