© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15352
    Prev
    Next
    INDEX
    Explanations

    positive sentiment words, especially "enjoy", as well as words paired with "the".

    oai_token-act-pair · gemini-2.0-flash

    enjoy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ^(@)
    -1.03
     ―――――
    -1.02
     Houſe
    -0.91
     tartalomajánló
    -0.88
    脚注の使い方
    -0.88
     doubtnut
    -0.87
     Shakspeare
    -0.85
     ――――――――
    -0.84
    ."));
    -0.84
    ſelves
    -0.83
    POSITIVE LOGITS
     the
    0.82
     a
    0.70
     some
    0.57
     The
    0.56
     par
    0.54
     this
    0.53
    !
    0.50
     what
    0.49
     peran
    0.48
     other
    0.47
    Activations Density 5.189%

    No Known Activations