© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13823
    Prev
    Next
    INDEX
    Explanations

    parts of words, especially prefixes and suffixes, in technical documents

    oai_token-act-pair · gemini-2.0-flash

    probability and letter combinations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    inerea
    -0.56
     کل
    -0.46
    recie
    -0.45
     rendre
    -0.43
     canais
    -0.42
    หลวง
    -0.42
     kal
    -0.42
     recurrent
    -0.42
    amazonaws
    -0.41
     Recurrent
    -0.40
    POSITIVE LOGITS
     Jop
    0.83
     Kapp
    0.82
     UIP
    0.79
    mybatisplus
    0.77
    Pp
    0.76
     AssemblyCulture
    0.76
    MigrationBuilder
    0.75
    UIP
    0.75
    bodyParser
    0.75
     Pompey
    0.75
    Activations Density 2.527%

    No Known Activations