© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14681
    Prev
    Next
    INDEX
    Explanations

    proper nouns referring to people, places, or organizations, including those related to the Congo conflict

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     myſelf
    -1.04
    ſelf
    -0.91
     purpoſe
    -0.87
     ſeveral
    -0.87
     Monfieur
    -0.85
     Jefus
    -0.85
     Majefty
    -0.83
     pleaſure
    -0.82
     chofe
    -0.82
     faſt
    -0.82
    POSITIVE LOGITS
    rostis
    0.59
    muck
    0.52
    NewGuid
    0.51
     ko
    0.50
    icycles
    0.49
    Diweddarwch
    0.48
    zbęd
    0.48
    يره
    0.48
     ev
    0.47
    idends
    0.47
    Activations Density 0.416%

    No Known Activations