© 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. 7967
    Prev
    Next
    INDEX
    Explanations

    sentences expressing possibility or ability

    oai_token-act-pair · gemini-2.0-flash

    can

    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
     photolibrary
    -1.02
    MLLoader
    -1.00
    WriteTagHelper
    -0.94
     myſelf
    -0.92
     itſelf
    -0.88
     Efq
    -0.87
    WebElementEntity
    -0.86
    abestanden
    -0.85
     незавершена
    -0.85
     CreateTagHelper
    -0.84
    POSITIVE LOGITS
    ’
    0.71
    '
    0.67
     rest
    0.47
     serve
    0.47
     perform
    0.46
     celebrate
    0.46
     include
    0.45
    mare
    0.44
     engage
    0.44
     play
    0.43
    Activations Density 2.046%

    No Known Activations