© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7792
    Prev
    Next
    INDEX
    Explanations

    anything being described as great, better, significant, or wonderful

    oai_token-act-pair · gemini-2.0-flash

    positive assessments or descriptors

    np_token-act-pair-logits · gpt-4o-mini

    great

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     tốt
    -0.52
    Portail
    -0.52
     terbaik
    -0.48
    baik
    -0.48
     greatly
    -0.48
     vry
    -0.47
     great
    -0.46
     very
    -0.46
     mucha
    -0.46
    ImageContext
    -0.45
    POSITIVE LOGITS
    хьтан
    0.72
    ViewFeatures
    0.71
    RefNanny
    0.66
    RegressionTest
    0.64
    Билгалдахарш
    0.63
    ⓧ
    0.61
     \%$\\
    0.61
     Extragalactic
    0.59
    ParallelGroup
    0.57
    InstrumentedTest
    0.57
    Activations Density 1.782%

    No Known Activations