© 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. 15981
    Prev
    Next
    INDEX
    Explanations

    the presence of years associated with events and words indicating newness or selection

    oai_token-act-pair · gemini-2.0-flash

    State fair/art show context

    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
    tagHelperRunner
    -0.97
     تضيفلها
    -0.93
    ########.
    -0.81
     EconPapers
    -0.73
     مشين
    -0.73
    évaluateur
    -0.73
     tartalomajánló
    -0.71
    jooq
    -0.69
    mybatisplus
    -0.68
     propOrder
    -0.68
    POSITIVE LOGITS
    ⭒
    0.48
     Serikat
    0.46
    ดับ
    0.44
     nisso
    0.43
     visualizations
    0.43
    globalData
    0.43
     FIBA
    0.42
    colnshire
    0.42
    Movies
    0.41
     rendu
    0.41
    Activations Density 11.078%

    No Known Activations