© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4193
    Prev
    Next
    INDEX
    Explanations

    a variety of symbols, markup, punctuation as well as the word "of"

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     myſelf
    -0.96
     fevere
    -0.89
     occaf
    -0.89
     raiſ
    -0.87
     faſt
    -0.85
     ſever
    -0.85
     pleaſure
    -0.84
     beſt
    -0.83
     poffe
    -0.82
     purpoſe
    -0.82
    POSITIVE LOGITS
     ‘
    0.58
     Fund
    0.57
     Über
    0.55
     Par
    0.52
     P
    0.51
    <eos>
    0.51
     Pre
    0.49
     S
    0.49
     '
    0.49
     Mon
    0.48
    Activations Density 1.984%

    No Known Activations