© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1759
    Prev
    Next
    INDEX
    Explanations

    spanish words interspersed in english text, especially words related to computer programming

    oai_token-act-pair · gemini-2.0-flash

    multiple languages and amounts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Dux
    -0.46
     Tema
    -0.46
    /*
    -0.43
    mouth
    -0.42
     astral
    -0.42
     Avenger
    -0.41
    uram
    -0.41
     avenger
    -0.41
    )))));
    -0.40
    ))));
    -0.40
    POSITIVE LOGITS
     समीक्षाओं
    0.94
    
    0.90
    IsMutable
    0.87
    Personensuche
    0.83
    uxxxx
    0.83
     autorytatywna
    0.79
    parsedMessage
    0.79
     nakalista
    0.78
     صوتيه
    0.77
    UnusedPrivate
    0.75
    Activations Density 0.413%

    No Known Activations