© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13153
    Prev
    Next
    INDEX
    Explanations

    a mix of German sentence structure and Russian language snippets about string manipulation

    oai_token-act-pair · gemini-2.0-flash

    foreign 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
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.62
     continúas
    -0.61
     Preisen
    -0.57
    Décès
    -0.55
    SuccessListener
    -0.55
    DropColumn
    -0.55
    AndEndTag
    -0.53
    FieldBuilder
    -0.53
    ModelAdmin
    -0.52
    MLLoader
    -0.52
    POSITIVE LOGITS
    tyczne
    0.70
    cyjne
    0.68
     französische
    0.67
     deutsche
    0.65
    amerikanische
    0.64
    ijne
    0.63
     связанные
    0.62
     ehemalige
    0.61
    nowe
    0.61
     Vorsitzende
    0.61
    Activations Density 1.341%

    No Known Activations