© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3307
    Prev
    Next
    INDEX
    Explanations

    words in Malaysian language and the names of businesses

    oai_token-act-pair · gemini-2.0-flash

    Malaysian language

    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
     Houſe
    -0.84
     pouvoit
    -0.82
    #+#
    -0.81
     Majefty
    -0.80
     ſever
    -0.80
     feroit
    -0.80
     AssemblyCompany
    -0.79
     ainfi
    -0.78
    ^(@)
    -0.76
     auroit
    -0.76
    POSITIVE LOGITS
     multi
    0.66
     מ
    0.65
     T
    0.65
     م
    0.65
    Multi
    0.64
     Multi
    0.64
     ب
    0.62
     un
    0.62
     E
    0.62
     Re
    0.62
    Activations Density 0.119%

    No Known Activations