© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10451
    Prev
    Next
    INDEX
    Explanations

    proper names whether place or person.

    oai_token-act-pair · gemini-2.0-flash

    Names and places

    np_max-act · gemini-2.0-flash

    surnames

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Monfieur
    -0.70
    RegressionTest
    -0.69
     ―――――
    -0.63
     whoſe
    -0.61
     verticale
    -0.61
     Hauteur
    -0.60
     ainfi
    -0.60
     firſt
    -0.59
     ――――――――
    -0.59
     murale
    -0.58
    POSITIVE LOGITS
    NoSuchAlgorithm
    0.67
     OnInit
    0.67
    forName
    0.64
     DialogInterface
    0.62
    AddTagHelper
    0.60
    ruptedException
    0.59
     المعيارى
    0.57
    évaluateur
    0.57
     iprot
    0.57
     II
    0.56
    Activations Density 4.112%

    No Known Activations