© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6454
    Prev
    Next
    INDEX
    Explanations

    the word 'air', sometimes followed by a hyphen and another word

    oai_token-act-pair · gemini-2.0-flash

    mentions of "air"

    np_token-act-pair-logits · gpt-4o-mini

    air

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     pleaſure
    -0.81
    Autoritní
    -0.81
     poffe
    -0.71
     autorytatywna
    -0.70
     Jefus
    -0.70
     myſelf
    -0.69
    InjectAttribute
    -0.69
     Monfieur
    -0.68
     Efq
    -0.68
     beſt
    -0.68
    POSITIVE LOGITS
     متعلقه
    0.64
    Hype
    0.44
     Lokales
    0.43
    guns
    0.42
    PropertyChanged
    0.42
    uaian
    0.41
    ومات
    0.39
     khảo
    0.39
     đô
    0.39
     hockey
    0.39
    Activations Density 0.382%

    No Known Activations