© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12958
    Prev
    Next
    INDEX
    Explanations

    mentions of studies, experiments, and limitations in research

    oai_token-act-pair · gemini-2.0-flash

    Negation and uncertainty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    Становништво
    -0.50
     therefore
    -0.50
    ServletRequest
    -0.50
     Anſ
    -0.49
    jsonwebtoken
    -0.48
     Gep
    -0.48
    hatenablog
    -0.48
     GlobalKey
    -0.47
     때문에
    -0.47
    既然
    -0.46
    POSITIVE LOGITS
     CreateTagHelper
    0.77
    httphttps
    0.75
    windowFixed
    0.73
    findpost
    0.71
     autorytatywna
    0.66
     للاسماء
    0.65
    RenderAtEndOf
    0.63
     Seeder
    0.62
    enumii
    0.60
     ligiloj
    0.58
    Activations Density 13.607%

    No Known Activations