© 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. 13878
    Prev
    Next
    INDEX
    Explanations

    German, Italian, or French words and/or other language specific characters, as well as URLs, suggesting the neuron may be detecting foreign languages and/or code.

    oai_token-act-pair · gemini-2.0-flash

    multiple languages/code

    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
    ReusableCell
    -0.84
    sidemargin
    -0.72
     szóci
    -0.67
    enumi
    -0.64
     beginnetje
    -0.64
     sapon
    -0.59
    AutoScaleMode
    -0.57
    ConstraintMaker
    -0.57
    DataMember
    -0.56
    principalColumn
    -0.56
    POSITIVE LOGITS
    <bos>
    1.24
    __':
    0.60
    Lähteet
    0.59
    __":
    0.52
    __':
    0.48
    Compartir
    0.47
    Gambas
    0.47
    __":
    0.47
     benne
    0.46
    Referencie
    0.46
    Activations Density 2.996%

    No Known Activations