© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5013
    Prev
    Next
    INDEX
    Explanations

    a mix of words, including "from scratch", words ending in "ly", percentages, and words with positive sentiment.

    oai_token-act-pair · gemini-2.0-flash

    scratch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     gyhoeddwyd
    -0.60
     mineures
    -0.56
     רבים
    -0.55
    VIAF
    -0.55
     Allegretto
    -0.54
     StatefulWidget
    -0.54
     Moderato
    -0.53
     parís
    -0.53
     getRule
    -0.53
     ceramica
    -0.52
    POSITIVE LOGITS
     completely
    0.97
     pure
    0.96
     fully
    0.88
    完全
    0.84
    pure
    0.83
     Completely
    0.81
     完全
    0.81
     sepenuhnya
    0.80
     entirely
    0.79
     totally
    0.79
    Activations Density 1.110%

    No Known Activations