© 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. 7940
    Prev
    Next
    INDEX
    Explanations

    variations of the word "cheap"

    oai_token-act-pair · gemini-2.0-flash

    cheap

    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
    er
    -1.00
     the
    -0.92
     a
    -0.83
     
    -0.79
     ‘
    -0.77
    ,
    -0.76
     many
    -0.73
     not
    -0.73
     I
    -0.71
     and
    -0.70
    POSITIVE LOGITS
     myſelf
    1.37
     itſelf
    1.30
     Efq
    1.29
     Theſe
    1.23
     auffi
    1.23
     ―――――
    1.22
     Houſe
    1.22
     themſelves
    1.22
     ་་
    1.18
     Jefus
    1.15
    Activations Density 0.971%

    No Known Activations