© 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. 14659
    Prev
    Next
    INDEX
    Explanations

    the word "tube", sometimes combined with other words related to geometry or science

    oai_token-act-pair · gemini-2.0-flash

    tube

    np_max-act · gemini-2.0-flash

    tube Method used: 1, reason: repeated "▁tube" tokens, explanation: tube

    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
    ſelves
    -1.01
     Anſ
    -0.98
     Theſe
    -0.96
     myſelf
    -0.96
     itſelf
    -0.95
    leſs
    -0.93
    ſelf
    -0.91
     Diſ
    -0.90
     ſeveral
    -0.90
     againſt
    -0.89
    POSITIVE LOGITS
     élevées
    0.84
     eccell
    0.76
     connus
    0.75
     âgées
    0.72
     bénévoles
    0.71
     malade
    0.71
     parvenir
    0.71
     rapides
    0.71
    ########.
    0.70
     connues
    0.69
    Activations Density 1.484%

    No Known Activations