© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14917
    Prev
    Next
    INDEX
    Explanations

    terminology related to technology, chemistry, medicine, and law.

    oai_token-act-pair · gemini-2.0-flash

    say "the ending -tively"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    Tikang
    -1.20
    Personendaten
    -1.09
    脚注の使い方
    -1.06
    ness
    -0.98
    ništvo
    -0.95
    цездатний
    -0.90
     kaarangay
    -0.83
     Roskov
    -0.83
    хьтан
    -0.81
    RenderAtEndOf
    -0.80
    POSITIVE LOGITS
    e
    0.92
    i
    0.78
    eeeeee
    0.75
    a
    0.73
     latter
    0.72
    tır
    0.69
     Stande
    0.66
    eeee
    0.66
    eee
    0.66
    เล
    0.63
    Activations Density 18.422%

    No Known Activations