© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5277
    Prev
    Next
    INDEX
    Explanations

    mentions of languages, especially non-English ones

    oai_token-act-pair · gemini-2.0-flash

    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
     speak
    -2.27
     speaks
    -2.00
     speaking
    -1.95
     Speak
    -1.90
     English
    -1.86
    speak
    -1.83
    Speak
    -1.74
     language
    -1.66
    speaking
    -1.66
    English
    -1.65
    POSITIVE LOGITS
     FetchType
    0.62
    astify
    0.59
     propOrder
    0.58
     CascadeType
    0.56
     "'");
    0.52
    wpi
    0.48
    /**
    0.47
    CardHeader
    0.47
    +#+#
    0.44
     GenerationType
    0.43
    Activations Density 0.370%

    No Known Activations