© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10056
    Prev
    Next
    INDEX
    Explanations

    gibberish and markup from multiple languages including Arabic and French combined with numbers and special characters

    oai_token-act-pair · gemini-2.0-flash

    multiple 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_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     s
    -0.71
     l
    -0.65
     go
    -0.64
     le
    -0.60
     o
    -0.58
     u
    -0.57
     d
    -0.57
     L
    -0.53
     v
    -0.52
     r
    -0.52
    POSITIVE LOGITS
     myſelf
    1.39
     itſelf
    1.38
     pleaſure
    1.32
    Personendaten
    1.29
     raiſ
    1.29
     ſever
    1.27
     ſche
    1.27
     houſe
    1.25
     ་་
    1.23
     Reſ
    1.22
    Activations Density 0.524%

    No Known Activations