© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12066
    Prev
    Next
    INDEX
    Explanations

    the word "was", and other past tense verbs

    oai_token-act-pair · gemini-2.0-flash

    Legal/technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    kháu
    -0.70
    ScopeManager
    -0.70
     pleaſure
    -0.69
     Theſe
    -0.63
     againſt
    -0.62
     Италијани
    -0.61
     Monfieur
    -0.60
    хіво
    -0.59
     Efq
    -0.59
     whoſe
    -0.59
    POSITIVE LOGITS
     jScrollPane
    0.49
     Po
    0.47
     po
    0.46
    tela
    0.46
    anas
    0.46
    PrototypeOf
    0.45
     pos
    0.44
    atta
    0.44
     G
    0.44
    ็จ
    0.43
    Activations Density 3.035%

    No Known Activations