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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3524
    Prev
    Next
    INDEX
    Explanations

    instructions for using computer software

    oai_token-act-pair · gemini-2.0-flash

    Software instructions

    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
    googleapis
    -0.65
    Of
    -0.48
    minipage
    -0.46
    EndContext
    -0.46
     happens
    -0.46
     Vierge
    -0.45
    ymce
    -0.45
    衆
    -0.43
    И
    -0.43
     plays
    -0.43
    POSITIVE LOGITS
     Commands
    0.80
     Initialise
    0.71
     EnglishChoose
    0.68
    Havolalar
    0.66
    yntaxException
    0.66
     Tags
    0.65
     JAXBElement
    0.64
     DBNull
    0.63
    Numerology
    0.63
     Outputs
    0.63
    Activations Density 9.064%

    No Known Activations