© 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. 2834
    Prev
    Next
    INDEX
    Explanations

    a variety of variables that are Portuguese or Spanish in origin, such as article/noun pairs or grammatical constructs common in those languages

    oai_token-act-pair · gemini-2.0-flash

    mixed language 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_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
    enumi
    -0.53
    othes
    -0.50
    bollah
    -0.50
    riller
    -0.49
    cherichia
    -0.48
    وش
    -0.48
    ilarities
    -0.46
    ">{{$
    -0.45
     Cri
    -0.44
    Bund
    -0.44
    POSITIVE LOGITS
     Paglinawan
    0.79
     ویکی‌پدیای
    0.73
     تضيفلها
    0.69
     Vikipedi
    0.68
     فريبيس
    0.65
    Geplaatst
    0.63
     kaynağından
    0.63
    DockStyle
    0.62
    Biographie
    0.62
    GraphicsUnit
    0.59
    Activations Density 0.444%

    No Known Activations