© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15938
    Prev
    Next
    INDEX
    Explanations

    mixed Russian and English words, specifically related to cataloging and software code

    oai_token-act-pair · gemini-2.0-flash

    Non-English / code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     '\\;'
    -0.54
     مرئيه
    -0.51
     wrecks
    -0.51
    GEBURTSDATUM
    -0.51
    RuleContext
    -0.49
     APPLICABLE
    -0.49
    serves
    -0.48
    effectively
    -0.48
    easily
    -0.48
     Meksiku
    -0.47
    POSITIVE LOGITS
     Jefus
    0.72
     Eſ
    0.68
     ägg
    0.67
     fumée
    0.66
     bonté
    0.66
     chré
    0.66
     Monfieur
    0.65
     Diſ
    0.64
     pitié
    0.64
     peindre
    0.63
    Activations Density 3.715%

    No Known Activations