© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15303
    Prev
    Next
    INDEX
    Explanations

    Italian words, particularly names and place names.

    oai_token-act-pair · gemini-2.0-flash

    Mixed topics and languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    astify
    -0.64
    ConstraintMaker
    -0.59
     Normdatei
    -0.56
     quæ
    -0.56
     فريبيس
    -0.56
    BorderFactory
    -0.54
    IntoConstraints
    -0.54
    脚注の使い方
    -0.52
     biens
    -0.52
     FormData
    -0.51
    POSITIVE LOGITS
     protoimpl
    0.63
    gwin
    0.60
    etCode
    0.60
    SpringBootTest
    0.55
    ρχ
    0.54
    etcode
    0.52
    ize
    0.52
    évaluateur
    0.51
    IZE
    0.50
     "..\..\..\
    0.49
    Activations Density 0.172%

    No Known Activations