© 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. 9222
    Prev
    Next
    INDEX
    Explanations

    discussions about healthcare, particularly preventative care for seniors

    oai_token-act-pair · gemini-2.0-flash

    repetitive online text

    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
     betweenstory
    -0.75
     assuré
    -0.54
    mogat
    -0.53
    rrggbb
    -0.52
    omitempty
    -0.51
     personales
    -0.51
    acyjnych
    -0.50
    assertNotNull
    -0.50
    fromnode
    -0.49
     dessutom
    -0.49
    POSITIVE LOGITS
     again
    1.01
    Again
    0.89
     Again
    0.88
    again
    0.85
     AGAIN
    0.76
    AddTagHelper
    0.68
     novamente
    0.66
    再次
    0.60
     final
    0.59
    Portail
    0.59
    Activations Density 0.458%

    No Known Activations