© 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. 2925
    Prev
    Next
    INDEX
    Explanations

    words and phrases from the Malay language

    oai_token-act-pair · gemini-2.0-flash

    Non-English 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
    Negative Logits
     ogóle
    -0.54
     læ
    -0.52
     என்று
    -0.51
     producir
    -0.50
    طة
    -0.50
     بتوان
    -0.50
    量の
    -0.50
    bnf
    -0.49
     mellom
    -0.49
     paesi
    -0.49
    POSITIVE LOGITS
    KommentareTeilen
    0.82
    ContentAsync
    0.75
    enderror
    0.72
    abestanden
    0.71
    devamını
    0.69
    BufferException
    0.66
    sidemargin
    0.65
    theless
    0.65
    ActionCreators
    0.64
    +#+#
    0.63
    Activations Density 0.138%

    No Known Activations