© 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. 11788
    Prev
    Next
    INDEX
    Explanations

    the prefix "non" meaning "not"

    oai_token-act-pair · gemini-2.0-flash

    non

    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
     nont
    -0.67
     препратки
    -0.63
    BeginInit
    -0.63
     >=",
    -0.62
    PhysRev
    -0.60
    Diwedd
    -0.59
     typelib
    -0.59
    μων
    -0.58
     Exacts
    -0.58
    OGND
    -0.57
    POSITIVE LOGITS
     للمعارف
    0.56
     Desai
    0.52
    rsin
    0.50
    θέ
    0.50
    Whilst
    0.49
     Einwilligung
    0.49
     Whilst
    0.48
    Injectable
    0.47
     Moraes
    0.47
     וכו
    0.46
    Activations Density 1.429%

    No Known Activations