© 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. 4132
    Prev
    Next
    INDEX
    Explanations

    sentences with multiple auxiliary verbs or complex verb phrases.

    oai_token-act-pair · gemini-2.0-flash

    News articles

    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
     myſelf
    -0.85
     itſelf
    -0.84
     Efq
    -0.84
    tagHelperRunner
    -0.83
     Monfieur
    -0.79
     Theſe
    -0.78
     nahilalakip
    -0.77
    )";
    -0.76
    Personendaten
    -0.76
     Forumite
    -0.74
    POSITIVE LOGITS
    出版年
    0.54
    ValueStyle
    0.53
    tra
    0.48
    da
    0.47
     da
    0.44
    dat
    0.44
    una
    0.44
     aceites
    0.43
    tagHelper
    0.42
    en
    0.42
    Activations Density 1.346%

    No Known Activations