© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11274
    Prev
    Next
    INDEX
    Explanations

    the suffix 'ard' at the end of words

    oai_token-act-pair · gemini-2.0-flash

    ard

    np_max-act · gemini-2.0-flash

    ard

    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
     :
    -0.82
    HostException
    -0.76
     Meksiku
    -0.70
     Bourgoin
    -0.66
     nahilalakip
    -0.64
    WithIOException
    -0.60
     in
    -0.59
     est
    -0.57
     es
    -0.57
     at
    -0.57
    POSITIVE LOGITS
     Monfieur
    1.75
     Theſe
    1.66
     itſelf
    1.51
     myſelf
    1.49
     Jefus
    1.49
     pleaſure
    1.48
     ſeveral
    1.41
     Majefty
    1.40
     houſe
    1.40
     Houſe
    1.39
    Activations Density 0.547%

    No Known Activations