© 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. 12936
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting used in scientific or technical writing

    oai_token-act-pair · gemini-2.0-flash

    formal text

    np_max-act-logits · gemini-2.0-flash

    footnote markers

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     myſelf
    -0.84
     raiſ
    -0.83
     pleaſure
    -0.82
     unſ
    -0.81
     houſe
    -0.81
     uſ
    -0.79
     inſ
    -0.78
     itſelf
    -0.78
     fubject
    -0.77
     hierogly
    -0.75
    POSITIVE LOGITS
     And
    0.71
     réfrig
    0.70
     In
    0.70
     fermés
    0.69
     To
    0.69
     A
    0.69
     The
    0.69
     From
    0.66
     It
    0.65
     dépens
    0.65
    Activations Density 11.259%

    No Known Activations