© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4230
    Prev
    Next
    INDEX
    Explanations

    past-tense verbs related to official reports, publications,releases, studies, and recommendations made by official bodies or governments

    oai_token-act-pair · gemini-2.0-flash

    Announcements/publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Caratteristiche
    -0.45
     pilot
    -0.42
    <eos>
    -0.42
     Roskov
    -0.42
    flexible
    -0.42
     ma
    -0.41
    mailto
    -0.41
     flexible
    -0.40
    滋味
    -0.39
    Sinopse
    -0.39
    POSITIVE LOGITS
     itſelf
    0.96
     ſeveral
    0.89
     myſelf
    0.89
     themſelves
    0.88
     himſelf
    0.83
     Reſ
    0.80
     kasarigan
    0.77
     purpoſe
    0.77
     Houſe
    0.76
     onPostExecute
    0.75
    Activations Density 3.739%

    No Known Activations