© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13653
    Prev
    Next
    INDEX
    Explanations

    references to legal disputes, violence and/or dog interactions

    oai_token-act-pair · gemini-2.0-flash

    narrative/emotional texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     estekak
    -0.99
     EconPapers
    -0.94
     nahilalakip
    -0.92
    Autoritní
    -0.86
    
    -0.81
    providedIn
    -0.80
    webElementXpaths
    -0.80
    RTEE
    -0.79
    出版年
    -0.79
    AddTagHelper
    -0.77
    POSITIVE LOGITS
    athion
    0.54
    abia
    0.54
    atifying
    0.51
    isting
    0.48
     selling
    0.47
    ucing
    0.47
    vements
    0.45
     of
    0.45
     tapping
    0.41
    atifs
    0.41
    Activations Density 5.183%

    No Known Activations