© 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. 2710
    Prev
    Next
    INDEX
    Explanations

    C++ code

    oai_token-act-pair · gemini-2.0-flash

    code/math symbols

    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
     fermés
    -0.80
     rapides
    -0.79
     peindre
    -0.77
     présentés
    -0.77
     médicaux
    -0.77
    følgelig
    -0.76
     réaliste
    -0.76
     avancée
    -0.75
     Record
    -0.75
     découver
    -0.74
    POSITIVE LOGITS
     hierogly
    0.36
     quadr
    0.36
    4
    0.35
     inflo
    0.35
    0
    0.35
    5
    0.35
     ebony
    0.33
    3
    0.32
    7
    0.31
    1
    0.31
    Activations Density 11.657%

    No Known Activations