© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6411
    Prev
    Next
    INDEX
    Explanations

    words that express a lack of something

    oai_token-act-pair · gemini-2.0-flash

    insufficient

    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
     Efq
    -1.67
     Theſe
    -1.45
     houſe
    -1.44
     Monfieur
    -1.42
     Jefus
    -1.37
     myſelf
    -1.36
     Савезне
    -1.34
     photolibrary
    -1.31
     ſeveral
    -1.31
     $_"
    -1.30
    POSITIVE LOGITS
     to
    0.97
    ,
    0.96
     in
    0.92
     and
    0.89
     a
    0.87
     e
    0.82
     en
    0.82
     n
    0.82
     at
    0.80
     no
    0.79
    Activations Density 1.693%

    No Known Activations