© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12524
    Prev
    Next
    INDEX
    Explanations

    words that are both common and also appear in the context of something notable

    oai_token-act-pair · gemini-2.0-flash

    well

    np_max-act-logits · gemini-2.0-flash
    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
     lenker
    -0.88
    oges
    -0.62
    出版年
    -0.61
    KommentareTeilen
    -0.61
    defineProperty
    -0.58
    NOPQRST
    -0.57
    XtraGrid
    -0.57
    balleur
    -0.56
    +#+#
    -0.55
     للاسماء
    -0.55
    POSITIVE LOGITS
     well
    3.22
    well
    2.59
    Well
    2.53
     Well
    2.39
     WELL
    2.27
    WELL
    2.17
     bien
    1.66
    wells
    1.56
     dobrze
    1.39
     wells
    1.36
    Activations Density 6.581%

    No Known Activations