© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3578
    Prev
    Next
    INDEX
    Explanations

    hyphenated words or words that can stand alone, but also finds words related to research.

    oai_token-act-pair · gemini-2.0-flash

    stand

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Efq
    -0.85
     reaſon
    -0.84
     دیکھیے
    -0.83
     Monfieur
    -0.82
     ſtate
    -0.81
     snippetHide
    -0.80
     fubject
    -0.80
     Chriftian
    -0.79
    oa̍t
    -0.79
    ########.
    -0.78
    POSITIVE LOGITS
    ings
    0.59
    hi
    0.57
    up
    0.54
    ung
    0.54
    as
    0.51
    ida
    0.50
    ua
    0.49
    ga
    0.48
    nt
    0.47
    back
    0.45
    Activations Density 13.122%

    No Known Activations