© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11424
    Prev
    Next
    INDEX
    Explanations

    text with mixed English and other languages relating to web links and account confirmation on Facebook.

    oai_token-act-pair · gemini-2.0-flash

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Na
    -0.54
     Po
    -0.52
     revanche
    -0.52
     then
    -0.52
     Za
    -0.50
     Nak
    -0.47
    Za
    -0.46
     na
    -0.46
     Z
    -0.46
     po
    -0.45
    POSITIVE LOGITS
    rungsseite
    0.71
    Referanser
    0.67
    WebVitals
    0.59
    脚注の使い方
    0.58
    Revenir
    0.58
     gyhoeddwyd
    0.57
    Viitteet
    0.55
    Personendaten
    0.55
     समीक्षक
    0.55
    קישורים
    0.54
    Activations Density 0.719%

    No Known Activations