© 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. 12422
    Prev
    Next
    INDEX
    Explanations

    smaller than signs in code snippets

    oai_token-act-pair · gemini-2.0-flash

    <

    np_max-act · gemini-2.0-flash
    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
     nostru
    -0.55
     dezvol
    -0.52
    WriteTagHelper
    -0.50
     frattempo
    -0.50
    Morfo
    -0.50
     Nutzungs
    -0.50
     communiquez
    -0.49
     isolado
    -0.49
    ]-->
    -0.49
     vermelhas
    -0.49
    POSITIVE LOGITS
     للمعارف
    0.87
    ValueStyle
    0.76
     nahilalakip
    0.74
    Personensuche
    0.68
     autorytatywna
    0.65
    WebElementEntity
    0.63
    ieteur
    0.63
    のですか
    0.58
    ](#
    0.58
    ranton
    0.57
    Activations Density 0.125%

    No Known Activations