© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13414
    Prev
    Next
    INDEX
    Explanations

    words related to appliances and mechanical devices

    oai_token-act-pair · gemini-2.0-flash

    Elevators and doors

    np_max-act · gemini-2.0-flash

    long-s spelling

    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_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     qu
    -0.55
     n
    -0.50
     con
    -0.49
     bus
    -0.48
     pro
    -0.46
    casio
    -0.46
    "?>
    -0.46
     anti
    -0.45
     Raw
    -0.45
     nor
    -0.43
    POSITIVE LOGITS
     myſelf
    1.11
     itſelf
    1.09
     raiſ
    1.06
     purpoſe
    0.98
     faſt
    0.96
     pleaſure
    0.96
     leſs
    0.94
     Monfieur
    0.94
     ſever
    0.93
     fevere
    0.93
    Activations Density 0.985%

    No Known Activations